INDEX
    Explanations

    references to individuals involved in legal or medical situations

    New Auto-Interp
    Negative Logits
    ience
    -0.14
    rub
    -0.13
    _DECL
    -0.13
    izzo
    -0.13
    iness
    -0.13
    ymb
    -0.13
    /memory
    -0.13
    hi
    -0.13
    inen
    -0.13
    IG
    -0.12
    POSITIVE LOGITS
    usercontent
    0.18
    tÃŃ
    0.17
    bjerg
    0.16
     ngoại
    0.15
    erdale
    0.15
    ois
    0.15
     subsidi
    0.14
    undo
    0.14
    gart
    0.14
    ohana
    0.14
    Act Density 0.469%

    No Known Activations