INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    t
    1.12
    an
    1.00
     as
    0.95
     an
    0.93
    s
    0.86
    ä
    0.84
    is
    0.79
    à
    0.78
    ch
    0.77
    ará
    0.77
    POSITIVE LOGITS
    ה
    0.80
    K
    0.74
    اوی
    0.73
     commandes
    0.71
     coppia
    0.70
    0.66
     чого
    0.66
     teléfonos
    0.65
    Mga
    0.65
     mettre
    0.64
    Act Density 0.001%

    No Known Activations