INDEX
    Explanations

    references to being trapped or confined

    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.93
     resourceCulture
    -0.68
    Diwedd
    -0.67
     <<<<<<<<<<<<<<
    -0.63
     فريبيس
    -0.59
    asche
    -0.57
    EndGlobalSection
    -0.57
     Divider
    -0.56
    Personensuche
    -0.56
    withIdentifier
    -0.55
    POSITIVE LOGITS
     trapped
    2.44
     trapping
    1.83
     stuck
    0.96
    stuck
    0.73
     atrap
    0.72
     entra
    0.69
    Stuck
    0.69
     stranded
    0.68
     Stuck
    0.68
    ГЛА
    0.59
    Act Density 0.000%

    No Known Activations