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

    Neuronpedia

    INDEX
    Explanations

    phrases that articulate connections or implications in logical arguments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
    InstanceState
    -0.58
    ѓ
    -0.55
    endiri
    -0.54
     Medication
    -0.53
     camicia
    -0.53
     ketahui
    -0.53
    kuuta
    -0.51
     élevées
    -0.50
     asistente
    -0.49
    POSITIVE LOGITS
    Datuak
    0.72
    extAlignment
    0.67
     nahilalakip
    0.66
     BoxFit
    0.61
    منابع
    0.59
    mtable
    0.58
    FieldNumber
    0.57
    textTheme
    0.54
     חיצוניים
    0.52
    enterOuterAlt
    0.52
    Act Density 0.019%

    No Known Activations