Several studies have examined the harms associated with the development of deepfake technology and its use by malicious actors, but less research has been devoted to deepfakes created by non-malicious creators and the ways people react to deepfakes developed without malicious intent. This study attempts to close this research gap through the exploration of two case studies that demonstrate non-malicious deepfake use on Instagram and Twitter. Using sensemaking, privacy as contextual integrity, and audience theory to guide the analysis of publicly available posts, tweets, and records, this study examines how people interact with and react to non-malicious deepfakes online. Building on these findings, this thesis suggests how social media platforms might integrate signifiers in their design that afford sensemaking for those interacting with deepfake technology and discusses how ethical frameworks and practices from values-oriented design and value-based engineering in design may help guide creators as they develop deepfake technology videos and applications for non-malicious purposes.