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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or assessments of performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.67
    EndGlobalSection
    -0.66
    Билгалдахарш
    -0.60
     otomatig
    -0.60
    hoeddwyd
    -0.59
     المعيارى
    -0.59
     مشين
    -0.59
    contentLoaded
    -0.58
     esternos
    -0.57
     للمعارف
    -0.56
    POSITIVE LOGITS
    例外
    0.87
     exception
    0.76
     exceptions
    0.67
     no
    0.60
     Exception
    0.59
     excepción
    0.59
     Exceptions
    0.57
     case
    0.57
    exception
    0.56
     excep
    0.56
    Act Density 0.139%

    No Known Activations