INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ükemmel
    -0.57
    símbolo
    -0.51
    pośred
    -0.50
     naturen
    -0.49
    #
    -0.49
    +
    -0.48
    /@
    -0.47
     législation
    -0.47
    əm
    -0.47
    +/
    -0.47
    POSITIVE LOGITS
    s
    0.77
    ValueStyle
    0.76
    e
    0.72
    Personensuche
    0.68
    GEBURTSDATUM
    0.66
     transfieras
    0.65
    msgTypes
    0.64
     Pristupljeno
    0.64
     autorytatywna
    0.64
    eq
    0.63
    Act Density 0.091%

    No Known Activations