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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and punctuation that indicate direct speech or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ObjectID
    -0.59
    าร์
    -0.55
    setArguments
    -0.55
    GEBURTSDATUM
    -0.54
     رأ
    -0.52
    Roth
    -0.52
     offense
    -0.51
    ًا
    -0.50
    Attrs
    -0.50
     hervor
    -0.50
    POSITIVE LOGITS
    ".
    2.46
    ”.
    2.39
    '.
    2.19
    ’.
    2.03
    )".
    1.99
    )”.
    1.88
    !".
    1.88
     ".
    1.81
    ?".
    1.80
    ...".
    1.76
    Act Density 0.122%

    No Known Activations