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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     settimana
    -0.55
    ни
    -0.47
     ,
    -0.47
    Ethylbenzene
    -0.47
     řed
    -0.47
     brancas
    -0.47
    putInt
    -0.46
     nyom
    -0.46
    Ferdin
    -0.46
     Nieder
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.97
     متعلقه
    0.91
    saraba
    0.82
    IUrlHelper
    0.79
    __(/*!
    0.79
    Vidite
    0.77
    idopsis
    0.74
     tslint
    0.73
    Aiheesta
    0.72
     insuffisamment
    0.71
    Act Density 0.022%

    No Known Activations