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

    Neuronpedia

    INDEX
    Explanations

    references to strategy and comparison using chess metaphors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ALIAS
    -0.15
     Getter
    -0.14
    oha
    -0.14
    egot
    -0.14
    óż
    -0.13
     заклад
    -0.13
     tub
    -0.13
    abr
    -0.13
     crew
    -0.13
    Alias
    -0.13
    POSITIVE LOGITS
     pawn
    0.31
     bishop
    0.30
     Pawn
    0.30
     knight
    0.29
     pieces
    0.28
    Pawn
    0.28
    bishop
    0.28
     bishops
    0.28
     Pieces
    0.27
     chess
    0.27
    Act Density 0.006%

    No Known Activations