INDEX
    Explanations

    Foreign language words, numbers, and sentence starts

    New Auto-Interp
    Negative Logits
     tę
    -1.00
    رابط
    -0.90
    cVar
    -0.86
     vár
    -0.85
     ausge
    -0.82
    /#/
    -0.81
     mė
    -0.79
     alliés
    -0.78
     for
    -0.77
    primaryColor
    -0.76
    POSITIVE LOGITS
    0.81
     Brésil
    0.81
     zů
    0.79
    سرائيل
    0.79
     tắm
    0.77
     médico
    0.77
     emite
    0.77
     Genu
    0.75
    hitheater
    0.75
    successful
    0.75
    Act Density 0.001%

    No Known Activations