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

    Neuronpedia

    INDEX
    Explanations

    references to authority and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.66
    Personendaten
    -0.64
     الاطلاع
    -0.63
     يتيمه
    -0.63
    Jeografia
    -0.58
    expandindo
    -0.54
     Geiſt
    -0.54
     فريبيس
    -0.54
     laſſen
    -0.52
    adpleegd
    -0.52
    POSITIVE LOGITS
     authority
    0.79
     Authority
    0.67
    authority
    0.63
     household
    0.61
    Authority
    0.60
     autorité
    0.57
     governor
    0.56
     AUTHORITY
    0.55
    Household
    0.52
     Household
    0.51
    Act Density 0.136%

    No Known Activations