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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences involving punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.69
    (
    -0.59
    ↵↵
    -0.58
     (
    -0.56
    orkin
    -0.56
    —
    -0.55
     I
    -0.53
    '
    -0.53
    ين
    -0.52
    /
    -0.51
    POSITIVE LOGITS
    HomeAsUpEnabled
    1.03
     Roskov
    1.00
    .",
    1.00
    $.}
    0.99
     ویکی‌پدیا
    0.99
    .!
    0.97
    .,"
    0.97
    .-
    0.97
    .*")]
    0.97
    .',
    0.96
    Act Density 0.955%

    No Known Activations