INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    dır
    1.00
    the
    0.97
    times
    0.89
     be
    0.86
    0.86
    0.86
    ğı
    0.84
    to
    0.84
    ta
    0.84
     بانک
    0.83
    POSITIVE LOGITS
     Dishes
    1.20
    1.13
     dishes
    1.09
    al
    1.03
     Григо
    1.02
     Dish
    0.99
    Dish
    0.97
     Ι
    0.96
    0.95
    "
    0.94
    Act Density 0.008%

    No Known Activations