An intervention benign at context v4<0.75 produces a class-C behavioral flip at 0.75<v4<1, demonstrating dormant behavioral changes from latent divergence

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

• A minimal prompt change can flip behavior.quote0.756
  Illustrates sensitivity to anchors.
• Interventions along activation manifold M_h yield behavioral trajectories following behavior manifold M_y, and vice versa — bidirectional relationship demonstrated across language models and video world models.finding0.751
  Central empirical result showing causal coupling between representation and behavior geometry across multiple substrates and modalities.
• Dormant Behavioral Changesconcept0.749
  Perturbations behaviorally null in one context but altering behavior in another due to latent divergence
• Persistent conversational context that produced emotion-relevant activations is a plausible driver of observed persistence resultsclaim0.749
  Authors' caveat that conversational context persistence rather than internal emotion state persistence could explain findings
• Fine-tuned behaviors are low-rank in weight space, potentially making them easier to manipulate with steering vectors compared to naturalistic behaviorclaim0.747
  Cited from Wang et al. 2025a as reason SDF is preferred over demonstration fine-tuning for realistic model organisms.
• Under spatio permutation controls, IIT consciousness estimates outperform Span Representation in mean AUC in several cases (LLaMA3.1-70B on Hinting and Irony, Mistral-7B on Irony, LLaMA3.1-8B on Strange Stories).finding0.746
  Contrasts with temporal permutation where Span Representation dominates; suggests spatio permutation reveals different dynamics.
• Cross-base fine-tuning yields asymmetric transfer: B10 transfers most robustly, B9 leastfinding0.746
  In-base gains accompanied by uneven OOD drops; higher-density priors more robust.
• Divergence within the behavioral null-space is harmless to functional claims about a function's computation when the claim ignores internal sub-computationsclaim0.745
  Key theoretical claim distinguishing harmless from pernicious divergence