language models recapitulate cyclic structure of human concepts from pretraining data

{
  "doc": "steering.md",
  "context": "Explanation for why manifold geometry emerges: implicit structure in training data (co-occurrence patterns) shapes internal representations.",
  "category": "ai",
  "norm_label": "language models recapitulate cyclic structure of human concepts from pretraining data",
  "graphify_id": "cyclic_data_structure",
  "source_file": "steering.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/steering/graph.json",
  "extracted_type": "hypothesis",
  "source_location": "§Case study: days of the week",
  "graphify_file_type": "hypothesis"
}