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

    Neuronpedia

    INDEX
    Explanations

    formal titles and respectful forms of address in dialogue

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fulness
    -0.55
    DebuggerNonUser
    -0.49
    béco
    -0.49
    leitung
    -0.49
    Билгалдахарш
    -0.49
     Si
    -0.48
    felder
    -0.48
     تعدى
    -0.48
    وروبا
    -0.47
    erapeutics
    -0.47
    POSITIVE LOGITS
     nakalista
    0.77
     سكانية
    0.70
     HasFactory
    0.61
    AnchorStyles
    0.60
    localctx
    0.58
    Бахар
    0.57
     Puntos
    0.55
    onViewCreated
    0.55
    ImageContext
    0.55
    XmlEnum
    0.53
    Act Density 0.010%

    No Known Activations