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

    Neuronpedia

    INDEX
    Explanations

    patterns of logical conditions and comparisons in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.76
     дописавши
    -0.68
    EndProject
    -0.65
     distanciation
    -0.65
    SourceChecksum
    -0.64
    InitVars
    -0.63
     cherchés
    -0.60
    OrBuilder
    -0.59
    Попис
    -0.59
     EconPapers
    -0.58
    POSITIVE LOGITS
     pieces
    1.02
     Pieces
    0.94
    Pieces
    0.90
    Piece
    0.90
    pieces
    0.89
    piece
    0.89
     pawns
    0.89
     piece
    0.88
     Piece
    0.88
     chess
    0.87
    Act Density 0.123%

    No Known Activations