INDEX
    Explanations

    references to Muslims and the Muslim community

    New Auto-Interp
    Negative Logits
    asca
    -0.15
    опиÑģ
    -0.15
     Ukra
    -0.15
    à¥Ĥप
    -0.15
    ë°ľ
    -0.14
    conde
    -0.14
    ì¶Ķ
    -0.14
    ìĹĨìĿĮ
    -0.14
    Ñĥг
    -0.14
    alis
    -0.14
    POSITIVE LOGITS
     Bullet
    0.16
    anger
    0.15
     Arabs
    0.15
    olland
    0.15
    Bullet
    0.14
    ebi
    0.14
    éf
    0.14
    utton
    0.14
    (s
    0.14
    ELLOW
    0.14
    Act Density 0.002%

    No Known Activations