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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CF
    -0.41
    ばかり
    -0.40
    MS
    -0.40
    ΙΣ
    -0.40
    Al
    -0.40
    abstract
    -0.39
    중
    -0.39
    xy
    -0.39
    aron
    -0.39
    M
    -0.39
    POSITIVE LOGITS
    ьаж
    0.95
     Administrativna
    0.90
    UrlResolution
    0.89
     itſelf
    0.88
     ویکی‌پدی
    0.83
     ProtoMessage
    0.81
     NSCoder
    0.80
     myſelf
    0.80
    EndGlobalSection
    0.79
    省市镇
    0.79
    Act Density 0.363%

    No Known Activations