1/ Periodic reminder: decodable ≠ causally used.
Or, as we put it: Represented Is Not Computed.
New paper w/ the excellent Ishita Darade (not on BSky; www.linkedin.com/in/ishita-da...), an undergrad student: arxiv.org/abs/2605.22488
#representation #NeuroAI #neuroscience #interpretability
arxiv.org
Structured prompts require integrating components according to task-relevant relations. How a network implements this integration is often hard to judge in language or vision, where those relations ar...
