INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    !
    1.29
    ?
    1.17
    )
    1.00
     a
    1.00
    .
    0.95
    .!
    0.87
    ))
    0.84
    +
    0.80
    ,
    0.79
    anh
    0.77
    POSITIVE LOGITS
     polvo
    1.39
    s
    1.38
    ியில்
    1.27
     пы
    1.20
    ن
    1.11
     embarazada
    1.10
    u
    1.09
    in
    1.08
    h
    1.08
    ה
    1.07
    Act Density 0.008%

    No Known Activations