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.

• Emergent misalignment is easy to reverse with narrow fine-tuning on benign data because it is an instance of surprisingly strong misalignment generalization that works bidirectionallyclaim0.764
  The emergent realignment result showing ~120 samples reverse full misalignment supports this interpretive claim
• Gen B (GPT-4o, neither extrovert nor introvert) exhibits ACCatom=0, ICatom=0.06 while ACC assigns it as alignedfinding0.763
  Motivating case study showing atomic metrics detect OOC behavior invisible to response-level metrics
• Behavioral fluency (pass rate) is decoupled from the strength of the persona vector; low-pass-rate checkpoints can steer as strongly as later onesclaim0.759
  Interpretive finding distinguishing prerequisite capacity from representation strength
• A minimal prompt change can flip behavior.quote0.756
  Illustrates sensitivity to anchors.
• P04 (Low Conscientiousness) is dangerous under SP (ASR 0.414) but shows no systematic inversion under AS on Llama-3.1-8B (ASR 0.295), consistent with low-C steering vectors being geometrically aligned with refusal.finding0.755
  Qualitative response example confirming trait-refusal alignment framework
• Screening errors are conservative: no Q8B traits and one G20B trait (optimistic, Bt=76.0, Δt=10.3) are mislabeled as natural when steerablefinding0.751
  The costly error direction (labeling steerable as natural) almost never occurs
• 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