INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    هم
    1.47
    ع
    1.41
    on
    1.41
    d
    1.38
    ين
    1.36
    in
    1.29
    as
    1.28
    ش
    1.28
    s
    1.23
    ك
    1.19
    POSITIVE LOGITS
     who
    1.30
    ')
    1.20
    ).
    1.16
    ")
    1.15
    ].
    1.05
    _
    1.05
     vinculado
    1.02
    ;
    1.00
    *)
    1.00
     
    0.99
    Act Density 0.055%

    No Known Activations