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

    Neuronpedia

    INDEX
    Explanations

    instances of high numerical values or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
     sauvages
    -0.59
     polaire
    -0.55
     filed
    -0.55
     verticales
    -0.55
     Eigentum
    -0.54
     vícti
    -0.54
     profondità
    -0.54
     popoli
    -0.54
     habet
    -0.54
    POSITIVE LOGITS
     surla
    0.75
    ADVERTISEMENT
    0.70
    RELATED
    0.66
    <blockquote>
    0.65
    ALSO
    0.63
    Additionally
    0.63
    ✭✭
    0.61
     lenker
    0.61
    *$
    0.57
    出版年
    0.57
    Act Density 0.136%

    No Known Activations