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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting used in visual representation or reference contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archiviato
    -0.92
     فريبيس
    -0.83
    Демографія
    -0.79
    Identyfik
    -0.78
     ―――――
    -0.71
    DrawerToggle
    -0.70
    Jeografia
    -0.69
    فایل‌لار
    -0.68
     estimés
    -0.67
     tartalomajánló
    -0.66
    POSITIVE LOGITS
     ↑
    1.80
    ↑
    0.71
    ↑↑
    0.56
    shtml
    0.56
    <td>
    0.54
     çıkan
    0.53
     yoksa
    0.52
    кування
    0.51
    }}},
    0.51
    :],
    0.51
    Act Density 0.020%

    No Known Activations