INDEX
    Explanations

    references to violence and crime-related events

    preceding a period or comma

    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.84
    ScopeManager
    -0.71
    TagMode
    -0.68
    httphttps
    -0.66
     disambiguazione
    -0.65
    Personendaten
    -0.64
    AnimationsModule
    -0.64
    featureID
    -0.63
    :✨
    -0.62
     للاسماء
    -0.61
    POSITIVE LOGITS
    ).
    0.57
    .)
    0.53
    .).
    0.51
    ').
    0.48
     toutefois
    0.47
    ).}
    0.47
    .}
    0.46
    ».
    0.46
    ).\\
    0.45
    .")
    0.44
    Act Density 1.332%

    No Known Activations