INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ő
    -0.44
     coat
    -0.43
     propri
    -0.43
     infección
    -0.41
    og
    -0.39
    permitAll
    -0.39
    大神
    -0.38
     Orts
    -0.38
     mano
    -0.37
    Main
    -0.37
    POSITIVE LOGITS
     myſelf
    0.91
     pleaſure
    0.87
    +#+#
    0.84
     تضيفلها
    0.84
     AssemblyCompany
    0.82
     purpoſe
    0.80
     Reſ
    0.79
     Efq
    0.79
     Monfieur
    0.79
    sonian
    0.78
    Act Density 0.082%

    No Known Activations