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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific tags or codes in a structured format, possibly indicating the start of new sections or elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     or
    -0.86
     Or
    -0.80
     ή
    -0.67
    or
    -0.66
    Or
    -0.65
     OR
    -0.60
     atau
    -0.58
     или
    -0.54
     oder
    -0.54
     eller
    -0.54
    POSITIVE LOGITS
    <bos>
    0.93
     ſy
    0.86
     ſind
    0.85
     ་་
    0.84
    المشاركات
    0.83
    出版年
    0.81
     Anſ
    0.80
     Herodotus
    0.80
     Shaksp
    0.80
    évaluateur
    0.79
    Act Density 0.426%

    No Known Activations