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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.71
    rade
    -0.69
    rium
    -0.66
    liest
    -0.65
    sold
    -0.65
    folk
    -0.65
    Plan
    -0.61
     Resurrection
    -0.60
    Vill
    -0.59
     Mandal
    -0.59
    POSITIVE LOGITS
     percent
    0.97
    %"
    0.95
    %
    0.93
     000
    0.89
     consecutive
    0.86
     thousand
    0.83
     hours
    0.81
    º
    0.80
     million
    0.79
    th
    0.77
    Act Density 0.125%

    No Known Activations