Partial-dependence (PD) profiles are easy to explain and interpret, especially given their estimation as the mean of ceteris-paribus (CP) profiles. However, the profiles may be misleading if, for instance, explanatory variables are correlated. In many applications, this is the case. For example, in the apartment-prices dataset, one can expect that variables surface and number of rooms may be positively correlated, because apartments with a larger number of rooms usually also have a larger surface. Similarly, in the Titanic dataset, a positive association can be expected for the values of variables fare and class, as tickets in the higher classes are more expensive than in the lower classes. The chapter illustrates in more detail the behavior of PD, LD, and AL profiles for a model with an interaction between correlated explanatory variables. The LD and AL profiles are useful to summarize the influence of an explanatory variable on a model’s predictions.