INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     avoient
    -0.90
     enfans
    -0.88
     définiti
    -0.82
     mourut
    -0.76
     médec
    -0.74
     démocr
    -0.71
     scolaires
    -0.71
     الحره
    -0.70
    étoit
    -0.69
     étoient
    -0.69
    POSITIVE LOGITS
     of
    0.56
     pass
    0.53
    appé
    0.52
    .
    0.52
    pass
    0.49
    tre
    0.47
    ize
    0.47
    IGENCE
    0.47
     tre
    0.46
     ketones
    0.45
    Act Density 0.430%

    No Known Activations