INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ,
    -0.45
     enca
    -0.41
    utri
    -0.38
     bowls
    -0.38
    -
    -0.38
     or
    -0.37
     biomass
    -0.37
     recognisable
    -0.35
    rehen
    -0.34
    ướng
    -0.34
    POSITIVE LOGITS
     dedans
    0.87
     nôtre
    0.86
     traités
    0.83
     quelcon
    0.83
    horabuena
    0.82
     espagne
    0.80
     extérieurs
    0.79
     avoient
    0.77
     étoit
    0.77
     quæ
    0.77
    Act Density 0.035%

    No Known Activations