Implicit social cognitions are thought processes that are not accessible to conscious introspection. These automatic processes can be measured with simple computer tasks that do not rely on participants’ self-reports. Across a broad range of research areas (e.g., stereotyping; prejudice; consumer choice; health behavior), measures of implicit cognition have been shown to predict behavior particularly well if the behavior is associated with social desirability concerns and/or if a decision must be made spontaneously. Driving behavior is characterized by frequent decisions under time pressure; further, self-reports of the intention to drive safely (or not) are socially sensitive. Therefore, we examined automatic preferences towards safe and risky driving with a Go/No-go Association Task (GNAT). The results suggest that (1) implicit attitudes towards driving behavior can be measured reliably with the GNAT; (2) implicit attitudes towards safe driving versus towards risky driving may be separable constructs. We propose that research on driving behavior may benefit from routinely including measures of implicit cognition. A practical advantage is a lesser susceptibility to social desirability biases, compared to self-report methods. Pending replication in future research, the apparent dissociation between implicit attitudes towards safe versus risky driving that we observed may contribute to a greater theoretical understanding of the causes of unsafe and risky driving behavior.