INDEX
    Explanations

    references to crime and legal issues

    New Auto-Interp
    Negative Logits
     aforementioned
    -0.18
    INCLUDED
    -0.14
     Kostenlose
    -0.13
    arious
    -0.13
    eshire
    -0.13
    akens
    -0.13
     [â̦]↵↵
    -0.13
    iola
    -0.12
    é§ħå¾ĴæŃ©
    -0.12
    Có
    -0.12
    POSITIVE LOGITS
     prostitu
    0.12
    ,...↵↵
    0.12
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.11
     lesbi
    0.11
    _NS
    0.11
    yasal
    0.11
    strcasecmp
    0.11
     .↵↵↵↵
    0.11
    elere
    0.11
    ileÅŁ
    0.11
    Act Density 13.709%

    No Known Activations