Thinking aloud is widely used for usability evaluation. The validity of the method is, however, debatable because it is generally used in a relaxed way that conflicts with the prescriptions of the classic model for obtaining valid verbalisations of thought processes. This study investigates whether participants that think aloud in the classic or relaxed way behave differently compared to performing in silence. Results indicate that whereas classic thinking aloud has little or no effect on behaviour apart from prolonging tasks, relaxed thinking aloud affects behaviour in multiple ways. During relaxed thinking aloud participants took longer to solve tasks, spent a larger part of tasks on general distributed visual behaviour, issued more commands to navigate both within and between the pages of the websites used in the experiment, and experienced higher mental workload. Implications for usability evaluation are discussed.