INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    qing
    0.41
     برانيه
    0.40
    licos
    0.36
    0.35
     seeming
    0.35
     જવા
    0.34
    ollah
    0.33
    0.33
    clustering
    0.33
    лки
    0.33
    POSITIVE LOGITS
     according
    2.31
     согласно
    2.05
     conformément
    1.98
    according
    1.97
     According
    1.92
     وفق
    1.92
    According
    1.91
     volgens
    1.90
     zgodnie
    1.90
     σύμφωνα
    1.90
    Act Density 0.032%

    No Known Activations