Although so is a recognized discourse marker, little work has explored its uses in turn-taking, especially when it is not followed by additional speech. In this paper we explore the use of the discourse marker so as it pertains to turn-taking and turn-releasing. Specifically, we compare the duration and intensity of so when used to take a turn, mid-utterance, and when releasing a turn. We found that durations of turn-retaining tokens are generally shorter than turn-releases; we also found that turn-retaining tokens tend to be lower in intensity than the following speech. These trends of turn-taking behavior alongside certain lexical and prosodic features may prove useful for the development of speech-recognition software.