Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to games and puzzles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?}",
    -0.60
    EDEFAULT
    -0.55
    ²/
    -0.55
    脚注の使い方
    -0.51
    رشف
    -0.51
    щадь
    -0.49
    ("}\
    -0.49
    ("~/
    -0.47
    []]
    -0.47
    WritableDatabase
    -0.47
    POSITIVE LOGITS
     puzzle
    0.91
     riddle
    0.90
     riddles
    0.88
     Puzzle
    0.85
     guessing
    0.84
     puzzles
    0.84
     quiz
    0.84
     puzz
    0.78
    puzzle
    0.78
    Puzzle
    0.77
    Act Density 0.387%

    No Known Activations