method
active
method:orbit-detection-algorithm

Orbit Detection Algorithm

Heuristic algorithm using detrending, Hann windowing, and FFT to classify token-level limiting behavior as FixedPoint, Orbit, Slider, or Unknown

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • Task paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded
  • Flag actions taken for abnormal reasons.
  • Detection Scoremethod0.731
    LLM judge classification accuracy measuring interpretability; threshold 0.8.
  • thought detectionconcept0.719
    Task of detecting a model's internal thoughts; found by Lindsey (2026) to peak at ~2/3 depth in transformers.
  • OPTICS Algorithmmethod0.715
    Density-based clustering used within spectral coarse-graining approach.
  • Task where a random word is prefilled as the assistant's response, then the model is asked whether it intended to say that word, testing introspection on prior intentions.
  • Strategic filtering procedure that removes invalid trajectories and maintains optimal positive-to-negative trajectory ratio to stabilize training.
  • A possible circuit that triggers when activations deviate from expected values, hypothesized to underlie noticing injected thoughts.