INDEX
    Explanations

    references to legal statutes and regulations

    New Auto-Interp
    Negative Logits
    )";
    
    -0.79
    )];
    
    -0.65
    )");
    
    -0.64
    !")
    
    -0.64
    %";
    -0.63
     }}^{\
    -0.62
     Hä
    -0.62
     @"/
    -0.62
    !");
    
    -0.61
    onded
    -0.61
    POSITIVE LOGITS
    AnchorTagHelper
    0.60
     nationaux
    0.57
     piena
    0.56
     suffit
    0.56
     szabály
    0.54
     enfans
    0.53
     nazionale
    0.52
     vierge
    0.52
     morire
    0.51
     prêtres
    0.51
    Act Density 0.424%

    No Known Activations