INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    mtrl
    -0.60
     fédé
    -0.59
    évolution
    -0.59
     sandero
    -0.59
     étrangère
    -0.54
    well
    -0.54
    Décès
    -0.54
     esquer
    -0.52
    Well
    -0.52
    ører
    -0.50
    POSITIVE LOGITS
     AssemblyTitle
    0.77
    InjectAttribute
    0.73
    DockStyle
    0.73
    stateProvider
    0.62
    principalTable
    0.62
     AssemblyCompany
    0.60
    EndInit
    0.58
    #
    0.58
    ]));
    
    0.57
     protect
    0.56
    Act Density 0.164%

    No Known Activations