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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating warnings or cautionary statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    warnings and cautions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.52
     GenerationType
    -0.51
    /*
    -0.48
     فريبيس
    -0.47
    /**
    -0.42
     Tatsache
    -0.41
    LookAnd
    -0.41
     soddis
    -0.41
     endblock
    -0.40
    MigrationBuilder
    -0.40
    POSITIVE LOGITS
     warned
    0.84
     WARNING
    0.70
     advirtió
    0.69
    warning
    0.68
     warning
    0.68
     Warning
    0.65
     dangers
    0.64
    danger
    0.64
     danger
    0.64
    Warning
    0.63
    Act Density 0.009%

    No Known Activations