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

    Neuronpedia

    INDEX
    Explanations

    specific names or identifiers within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    :✨
    -0.78
    حياته
    -0.76
    новништво
    -0.75
    XmlAccessType
    -0.75
     виправивши
    -0.74
     nakalista
    -0.73
     كومونز
    -0.71
    matchCondition
    -0.68
    Hauptartikel
    -0.68
    )();
    -0.68
    POSITIVE LOGITS
     Мексичка
    0.44
    झ
    0.42
    mphony
    0.41
     deple
    0.40
     khẩu
    0.40
    ammer
    0.39
    keits
    0.38
    ধ্য
    0.38
     waard
    0.36
     للاسماء
    0.36
    Act Density 0.004%

    No Known Activations