INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     General
    -0.63
    General
    -0.57
     President
    -0.56
     president
    -0.46
     GENERAL
    -0.45
    President
    -0.44
     general
    -0.43
    <eos>
    -0.41
     coach
    -0.40
     governor
    -0.39
    POSITIVE LOGITS
     fermés
    1.01
     blessés
    0.93
     Abroad
    0.92
    UrlResolution
    0.92
     chré
    0.91
     meurt
    0.91
     ainfi
    0.90
     peindre
    0.90
     avoient
    0.89
     ouvriers
    0.89
    Act Density 0.215%

    No Known Activations