INDEX
    Explanations

    events related to crime and law enforcement

    New Auto-Interp
    Negative Logits
     leider
    -0.15
    serter
    -0.14
    adesh
    -0.14
    eter
    -0.14
    iras
    -0.14
    ndata
    -0.14
    utsch
    -0.14
    avic
    -0.14
    udeau
    -0.14
    utor
    -0.13
    POSITIVE LOGITS
    lius
    0.14
    lü
    0.14
     McGu
    0.14
    igate
    0.14
     cop
    0.13
     Half
    0.13
    cop
    0.13
     half
    0.13
     Irvine
    0.13
     your
    0.13
    Act Density 0.064%

    No Known Activations