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

    Neuronpedia

    INDEX
    Explanations

    height measurements in feet and inches

    oai_token-act-pair · gpt-3.5-turbo

    negative numeric values and references to weight measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mankind
    -0.76
     Solitaire
    -0.71
     Mayhem
    -0.71
     Redux
    -0.70
     Clash
    -0.70
     FML
    -0.69
     Pengu
    -0.68
     TODAY
    -0.67
    izu
    -0.66
     Saud
    -0.65
    POSITIVE LOGITS
    forward
    1.12
    interstitial
    1.03
    inches
    0.97
    area
    0.96
    based
    0.95
    interface
    0.92
    edge
    0.91
    transfer
    0.87
    function
    0.87
    border
    0.86
    Act Density 0.103%

    No Known Activations