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

    Neuronpedia

    INDEX
    Explanations

    the beginning of the document and the transition to new sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.61
    wahati
    -0.59
     maxn
    -0.58
     fér
    -0.55
    yargs
    -0.52
    exitRule
    -0.52
     snippetHide
    -0.50
     izd
    -0.50
     Enjoy
    -0.49
     Zia
    -0.48
    POSITIVE LOGITS
    ]$}
    0.70
    <bos>
    0.70
     ExecuteAsync
    0.63
    tagHelperRunner
    0.60
    CloseOperation
    0.59
    IsContent
    0.56
    ГЛА
    0.55
     للاسماء
    0.53
     محفوظة
    0.53
     الحره
    0.52
    Act Density 0.251%

    No Known Activations