INDEX
    Explanations

    phrases related to criminal activity and legal sentences

    New Auto-Interp
    Negative Logits
    809
    -0.15
    iddet
    -0.15
    Charts
    -0.15
    ktion
    -0.15
     Gemini
    -0.14
    794
    -0.13
    krom
    -0.13
     Rect
    -0.13
    ellig
    -0.13
     racks
    -0.13
    POSITIVE LOGITS
    .quote
    0.15
     cons
    0.14
    zilla
    0.14
    /ar
    0.14
    /svg
    0.14
    znám
    0.14
     addCriterion
    0.14
    zik
    0.14
    [at
    0.14
    ót
    0.13
    Act Density 0.070%

    No Known Activations