INDEX
    Explanations

    references to domestic and sexual violence

    New Auto-Interp
    Negative Logits
    ehir
    -0.15
    /document
    -0.15
    ternet
    -0.15
    andler
    -0.15
    illery
    -0.14
    gor
    -0.14
     Vad
    -0.14
    burst
    -0.14
    .getDocument
    -0.13
    //{{
    -0.13
    POSITIVE LOGITS
    olor
    0.16
     Spirits
    0.15
    ulin
    0.15
    anny
    0.15
    LOUR
    0.14
    nev
    0.14
     Jihad
    0.14
     Vladim
    0.14
    itating
    0.14
    Cancelable
    0.14
    Act Density 0.006%

    No Known Activations