INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     those
    -1.32
     despite
    -1.23
     these
    -1.22
     each
    -1.07
     there
    -1.05
     Despite
    -1.01
     their
    -0.93
     operativo
    -0.91
     first
    -0.90
     all
    -0.86
    POSITIVE LOGITS
    Bisous
    1.22
    1.19
    inguish
    1.15
     تھا
    1.12
    ÍNDICE
    1.05
    нью
    1.04
     ہوا
    1.00
    1.00
    0.98
    Presentación
    0.98
    Act Density 0.327%

    No Known Activations