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

    Neuronpedia

    INDEX
    Explanations

    references to the game of chess

    oai_token-act-pair · gpt-3.5-turbo

    references to chess and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.81
    aneous
    -0.78
    uated
    -0.75
    ibus
    -0.74
    phrine
    -0.74
    igious
    -0.73
    ient
    -0.71
    uating
    -0.70
    aneously
    -0.69
    erred
    -0.64
    POSITIVE LOGITS
     chess
    0.93
     rook
    0.82
    pai
    0.81
     Chess
    0.76
    bowl
    0.76
    cards
    0.76
     puzzles
    0.76
     puzzle
    0.75
    manship
    0.75
    board
    0.73
    Act Density 0.022%

    No Known Activations