INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     and
    -1.59
     démocr
    -0.89
    and
    -0.85
     cérami
    -0.79
     그리고
    -0.78
     chrétiens
    -0.77
     valamint
    -0.77
     nemlig
    -0.77
     fermés
    -0.76
     säll
    -0.75
    POSITIVE LOGITS
    /
    0.81
     therefore
    0.77
     also
    0.75
     possibly
    0.75
     whatnot
    0.75
     thus
    0.73
     then
    0.72
     other
    0.71
     maybe
    0.70
     ultimately
    0.69
    Act Density 1.645%

    No Known Activations