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

    Neuronpedia

    INDEX
    Explanations

    details related to criminal activities and transactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     foglal
    -0.48
    Tea
    -0.46
     forced
    -0.46
    rektor
    -0.45
    empio
    -0.44
    Personensuche
    -0.44
    alış
    -0.44
     Lesen
    -0.44
     κατά
    -0.43
     focused
    -0.43
    POSITIVE LOGITS
     referenties
    0.69
     виправивши
    0.68
    Vidite
    0.67
     Préférences
    0.65
    ंदीखरीदारी
    0.63
    actionMode
    0.59
    Билгалдахарш
    0.58
    UnsafeEnabled
    0.57
    openhague
    0.57
     podjela
    0.57
    Act Density 0.077%

    No Known Activations