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

    Neuronpedia

    INDEX
    Explanations

    backslashes used in code or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.90
    SharedDtor
    -0.88
    PMailer
    -0.81
    elemField
    -0.77
    ########.
    -0.75
    Composable
    -0.72
    Šaltiniai
    -0.72
     layui
    -0.71
    İstinadlar
    -0.70
     autorytatywna
    -0.69
    POSITIVE LOGITS
    \
    1.25
    <h3>
    0.94
    <h2>
    0.87
     ")");
    0.87
    <h4>
    0.84
    </tr>
    0.83
    enumerate
    0.77
    <h1>
    0.76
    We
    0.74
    )\
    0.72
    Act Density 0.058%

    No Known Activations