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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consistency or reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Petra
    -0.17
     wh
    -0.15
     mo
    -0.14
     Whitney
    -0.14
    acionales
    -0.14
    ought
    -0.14
    ulares
    -0.14
     cho
    -0.14
    '
    -0.14
    zan
    -0.14
    POSITIVE LOGITS
    //{{
    0.18
    Äįer
    0.16
    ForObject
    0.15
    *=*=
    0.15
    MDB
    0.15
    вол
    0.15
     anzeigen
    0.14
    ENCE
    0.14
    ofil
    0.14
    heel
    0.13
    Act Density 0.013%

    No Known Activations