INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.95
     sanitaires
    -0.92
     financières
    -0.90
     réguli
    -0.88
     culturelles
    -0.86
     насељу
    -0.85
     réunis
    -0.83
     énergé
    -0.81
     complètes
    -0.81
     juridiques
    -0.79
    POSITIVE LOGITS
    ity
    0.87
    ally
    0.66
     itſelf
    0.63
     syst
    0.53
    )));
    
    0.52
    arily
    0.52
    ITY
    0.50
     amounts
    0.50
     Maf
    0.50
     leaſt
    0.50
    Act Density 0.111%

    No Known Activations