Neural representations carry rich geometric structure; but does that structure causally shape behavior?

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

• Geometric structure of neural representations causally shapes model behaviorclaim0.904
  The paper's core causal assertion: geometry is not incidental but mechanistically linked to behavior
• Does the geometric structure of neural representations causally shape model behavior?question0.900
  The motivating research question of the paper
• Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.882
  Central hypothesis tested via manifold steering experiments across language models and video world models.
• geometric structure in neural network representations drives model behaviorclaim0.845
  Interpretive assertion that representation geometry is not epiphenomenal but causally shapes what models do externally.
• We hypothesize that representation geometry drives model behavior — the geometric structure of internal representations causally shapes what models do externally.hypothesis0.837
  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 behaviorclaim0.836
  Central empirical claim of the paper, demonstrated across tasks and modalities
• The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.claim0.825
  The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
• How does representation geometry causally drive model behavior?question0.816
  The central scientific question the paper addresses through the lens of interventional causality.