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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases, particularly those expressing apologies or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.73
    AnimationsModule
    -0.70
    KURZBESCHREIBUNG
    -0.68
    //
    -0.67
    ioutil
    -0.66
    VIAF
    -0.62
     @"/
    -0.61
    /*
    -0.60
     intStringLen
    -0.60
    enumi
    -0.60
    POSITIVE LOGITS
    Спољашње
    0.48
     isInitialized
    0.48
    Réponse
    0.45
     uska
    0.45
     válasz
    0.43
     générales
    0.42
     hari
    0.40
    gla
    0.40
    ten
    0.40
     averaging
    0.39
    Act Density 0.385%

    No Known Activations