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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to coding or technical elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    δά
    -0.49
     заключа
    -0.48
    foglal
    -0.48
     seier
    -0.47
    جستارهای
    -0.47
     vittoria
    -0.47
     îna
    -0.46
     Senado
    -0.45
     divider
    -0.45
    áč
    -0.45
    POSITIVE LOGITS
    帖最后由
    0.93
     חיצוניים
    0.77
    ⓘ
    0.76
    \{\\
    0.75
     للمعارف
    0.73
    Билгалдахарш
    0.72
    Спољашње
    0.71
    UnsafeEnabled
    0.71
    DockStyle
    0.69
    Externí
    0.69
    Act Density 0.355%

    No Known Activations