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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistical information in sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that include numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.86
    wcsstore
    -0.80
    NetMessage
    -0.70
     graz
    -0.70
     masc
    -0.70
     abduct
    -0.70
     dimensional
    -0.69
    tnc
    -0.69
     loaf
    -0.69
     splash
    -0.68
    POSITIVE LOGITS
     Including
    1.31
     Approximately
    1.26
     Among
    1.24
     Assuming
    1.21
     Rough
    1.16
     Estimates
    1.15
     Nearly
    1.14
     Compare
    1.14
     About
    1.10
    Percent
    1.09
    Act Density 0.474%

    No Known Activations