'Winner-take-all' competition among real and illusory words.

'Winner-take-all' networks are an important theoretical construct in visual neuroscience. An implication of winner-take-all networks is that a stimulus that wins the competition for selection receives maximal activation and will be consciously perceived, even when selection was incorrect. In this study, competition was induced between physically presented ('real') and self-constructed ('illusory') words. Semantic activation was probed by recording event-related potential responses to a downstream target word. The results showed that only words reported by participants triggered a spread of activation in the semantic system, whereas non-reported words failed to prime the target. Both effects were independent of whether the potential primes were 'real' or 'illusory'. Our findings indicate that neural 'winner-take-all' networks extend to the processing of lexical units.