Interpretability tools can reveal what 'feeling alive' looks like inside a neural network model.

{
  "doc": "/Users/antonborzov/Documents/Research.nosync/notes/RESEARCH-VECTORS.md",
  "claim": "Interpretability tools can reveal what 'feeling alive' looks like inside a neural network model.",
  "vector": "interpretability-as-microscope-for-consciousness",
  "section": "1. Bicycle for the Soul",
  "extracted_at": 1778899419,
  "extracted_by": "haiku-4-5",
  "supporting_refs": [
    "Goodfire Ember",
    "feature steering"
  ]
}