Humanoid robots are predicted to be increasingly present in the everyday life of millions of people worldwide. Humans make sense these artificial agents’ actions mainly through the attribution of human characteristics, a process called anthropomorphism. However, despite a large number of studies, how the representation of artificial agents is constructed remains an open question. Here, we aim at integrating the process of anthropomorphism into the cognitive control theory, that postulates that we adapt resources management for information processing according to the current situation. In three experiments, we manipulated the cognitive load of participants while being observed by a humanoid robot to investigate how it could impact the online adaptation of the mental representation of the robot. The first two experiments indicated an online control of demanding resources in order to switch from an intentional to a physical representation, therefore inhibiting anthropomorphic, i.e. social, inferences. The third experiment investigated how the goals of the observing robot, i.e. “what” versus “why” is the robot observing, influences the effect of the cognitive load, showing that an explicit focus on its intentionality automatically biases cognitive processes towards anthropomorphism, yielding insights on how we mentally represent interacting robots when cognitive control theory and robots’ anthropomorphism are considered together.