This paper introduces the implementation of a method for displaying terms in complex generalized linear models using R. The method, referred to as *effect displays*, involves constructing tables or graphs that show the fitted values of high-order terms in the model, while absorbing their lower-order relatives. The predictors in the high-order terms are allowed to range over their values, while other predictors are fixed at typical values such as the mean or median. The paper provides an example using data on police treatment of individuals arrested for marijuana possession in Toronto, where the probability of release is influenced by race, age, and other characteristics. The *effects* package in R is used to compute and visualize these effect displays, which can be particularly useful for interpreting interactions and higher-order terms in complex models. The package includes functions like `effect` and `all.effects` for constructing effect objects and generating plots, with options for customizing the display. The paper also discusses the handling of regression splines and orthogonal polynomials, and provides examples of effect displays for various models, including logistic regression and linear models with polynomial terms.This paper introduces the implementation of a method for displaying terms in complex generalized linear models using R. The method, referred to as *effect displays*, involves constructing tables or graphs that show the fitted values of high-order terms in the model, while absorbing their lower-order relatives. The predictors in the high-order terms are allowed to range over their values, while other predictors are fixed at typical values such as the mean or median. The paper provides an example using data on police treatment of individuals arrested for marijuana possession in Toronto, where the probability of release is influenced by race, age, and other characteristics. The *effects* package in R is used to compute and visualize these effect displays, which can be particularly useful for interpreting interactions and higher-order terms in complex models. The package includes functions like `effect` and `all.effects` for constructing effect objects and generating plots, with options for customizing the display. The paper also discusses the handling of regression splines and orthogonal polynomials, and provides examples of effect displays for various models, including logistic regression and linear models with polynomial terms.