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

    Neuronpedia

    INDEX
    Explanations

    mentions of aesthetic or design-related qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.66
    /***/
    -0.66
    InstrumentedTest
    -0.63
    出版年
    -0.60
    unehmen
    -0.59
     виправивши
    -0.58
    非常的
    -0.56
    XmlType
    -0.55
    onore
    -0.55
    picasso
    -0.55
    POSITIVE LOGITS
     lenker
    0.69
     bikin
    0.57
     Și
    0.57
    眼下
    0.56
    née
    0.56
     nemmeno
    0.55
    Пока
    0.55
     rigueur
    0.55
     goddamn
    0.54
     famously
    0.54
    Act Density 0.440%

    No Known Activations