INDEX
    Explanations

    references to theft and related criminal activities

    New Auto-Interp
    Negative Logits
    oluble
    -0.57
     criterio
    -0.50
    partimento
    -0.49
     Medien
    -0.47
     onError
    -0.47
     MyApp
    -0.47
    iyaki
    -0.46
     renou
    -0.46
    IVersion
    -0.45
     mostrarse
    -0.45
    POSITIVE LOGITS
     stealing
    1.14
     theft
    1.13
     steal
    1.12
     steals
    1.11
     stolen
    1.02
    theft
    1.02
    steal
    1.02
     stole
    1.01
     Theft
    0.99
     thief
    0.99
    Act Density 0.535%

    No Known Activations