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

    Neuronpedia

    INDEX
    Explanations

    low-frequency symbols and special characters within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .";
    -0.74
    !';
    -0.73
    )";
    -0.71
    ."),
    -0.70
    '));
    -0.69
    ."));
    -0.68
    .'”
    -0.68
    .';
    -0.67
    $.
    -0.67
    >--}}
    -0.66
    POSITIVE LOGITS
     (%)
    1.00
    </th>
    0.83
    (%)
    0.83
    (\%)
    0.80
     (\%)
    0.79
     (°
    0.74
    findpost
    0.73
    NameInMap
    0.72
     $(\%)$
    0.71
     للاسماء
    0.67
    Act Density 0.652%

    No Known Activations