INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ס
    1.05
    ای
    1.02
    ד
    0.95
    ۶
    0.92
    0.89
     ی
    0.86
    گ
    0.83
    0.82
    ता
    0.82
    7
    0.81
    POSITIVE LOGITS
    in
    0.87
    spiration
    0.79
     swelling
    0.73
     pageant
    0.73
     in
    0.70
     verb
    0.69
     customer
    0.69
     authorization
    0.68
     algorithm
    0.67
     controller
    0.66
    Act Density 0.000%

    No Known Activations