INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     dreaded
    1.15
     inactivity
    1.08
     impurities
    1.06
     laborious
    1.05
     perspiration
    1.00
    0.96
     drowsiness
    0.96
     камера
    0.95
     terribly
    0.95
     камеры
    0.93
    POSITIVE LOGITS
    破碎
    1.26
    Fragments
    1.25
     fragment
    1.13
     diálogo
    1.13
     टुक
    1.12
     Fragments
    1.09
     Teil
    1.09
     disintegr
    1.08
     trao
    1.08
     splinter
    1.08
    Act Density 0.133%

    No Known Activations