INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     الإمارات
    -0.08
     сақтау
    -0.08
     საბჭ
    -0.08
    apore
    -0.08
    يبة
    -0.07
     صبح
    -0.07
    -0.07
    ვისტ
    -0.07
     Հանր
    -0.07
     کړو
    -0.07
    POSITIVE LOGITS
     OL
    0.08
     coloring
    0.08
    ogl
    0.08
     লোক
    0.08
    andet
    0.07
     gand
    0.07
     exotic
    0.07
    horn
    0.07
     মানুষ
    0.07
    lya
    0.07
    Act Density 0.000%

    No Known Activations