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

    Neuronpedia

    INDEX
    Explanations

    information related to numeric types and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esternos
    -0.78
    出版年
    -0.73
    udesta
    -0.72
    ειτουργ
    -0.71
     препратки
    -0.68
    MLLoader
    -0.68
     autorytatywna
    -0.67
    aderie
    -0.66
    ướt
    -0.65
    RTLR
    -0.65
    POSITIVE LOGITS
     numeric
    0.93
     numbers
    0.91
     digits
    0.83
     numerical
    0.79
     数字
    0.78
    数字
    0.78
     numerals
    0.74
     number
    0.74
     Numer
    0.73
    digits
    0.71
    Act Density 0.476%

    No Known Activations