INDEX
    Explanations

    terms related to domestic violence and its victims

    New Auto-Interp
    Negative Logits
     Bene
    -0.17
    oby
    -0.16
    iah
    -0.15
    olit
    -0.15
     Eisen
    -0.14
    kses
    -0.14
    eren
    -0.14
    entanyl
    -0.14
    omb
    -0.13
    xy
    -0.13
    POSITIVE LOGITS
    achuset
    0.16
    erville
    0.15
     ox
    0.15
    üstü
    0.14
    bette
    0.14
    urdu
    0.14
    ettings
    0.14
    ongan
    0.14
    reur
    0.14
    angler
    0.14
    Act Density 0.007%

    No Known Activations