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

    Neuronpedia

    INDEX
    Explanations

    expressions related to causation or influence

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     raiſ
    -0.68
     itſelf
    -0.66
     Zd
    -0.64
    IsContent
    -0.62
     Wraith
    -0.61
     Scin
    -0.60
    onekana
    -0.60
     Quint
    -0.60
     autorytatywna
    -0.60
     drives
    -0.58
    POSITIVE LOGITS
     scolaires
    0.67
    SequentialGroup
    0.65
     оригіналу
    0.62
    γγε
    0.60
    ebvre
    0.58
     hohem
    0.57
    PreferredItem
    0.56
    CopyWith
    0.55
     lehetős
    0.54
     religieuses
    0.54
    Act Density 0.079%

    No Known Activations