INDEX
    Explanations

    references to drug-related incidents and illegal activities

    New Auto-Interp
    Negative Logits
    ToFit
    -0.15
     prostituer
    -0.14
    blink
    -0.14
    ennie
    -0.14
    emens
    -0.14
     Stout
    -0.14
     Deniz
    -0.14
    UnderTest
    -0.14
    652
    -0.13
     aalborg
    -0.13
    POSITIVE LOGITS
    annis
    0.16
     paraph
    0.15
     onBind
    0.15
     eins
    0.14
    yan
    0.14
    eshire
    0.14
    keit
    0.14
    acey
    0.13
    ypress
    0.13
    atts
    0.13
    Act Density 0.027%

    No Known Activations