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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.89
     Efq
    -0.81
     itſelf
    -0.78
    NUMX
    -0.76
     }}$}
    -0.75
    RSpec
    -0.73
    Искәрмәләр
    -0.73
     myſelf
    -0.72
     Paglinawan
    -0.71
     NgModule
    -0.71
    POSITIVE LOGITS
     ولد
    0.53
     [
    0.53
    fır
    0.49
     Zelle
    0.48
    ők
    0.46
    tifkan
    0.46
    发表于
    0.45
     ग्राहक
    0.45
    Activité
    0.45
    ISupport
    0.45
    Act Density 0.131%

    No Known Activations