Does the geometric structure of neural representations causally shape model behavior?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Neural representations carry rich geometric structure; but does that structure causally shape behavior?quote0.900
  Opening sentence framing the paper's core inquiry.
• geometric structure in neural network representations drives model behaviorclaim0.871
  Interpretive assertion that representation geometry is not epiphenomenal but causally shapes what models do externally.
• does that structure causally shape behavior?question0.869
  Opening question: does the rich geometric structure of neural representations have a causal role in behavior?
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.868
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.866
  The causal hypothesis motivating the use of causality (intervention) as the lens connecting representation and behavior geometry.
• There exists a bidirectional relationship between the geometry of neural representation and the geometry of model behaviorclaim0.860
  Central empirical claim of the paper, demonstrated across tasks and modalities
• How does representation geometry causally drive model behavior?question0.858
  The central scientific question the paper addresses through the lens of interventional causality.
• causal shaping of behavior by representation geometryconcept0.852
  Central question: does geometry in activation space causally determine behavior?