INDEX
    Explanations

    mentions of law enforcement agencies and their activities

    New Auto-Interp
    Negative Logits
    ÑģÑĤи
    -0.17
    URT
    -0.16
    .registry
    -0.15
    aniu
    -0.14
    usive
    -0.14
    LAY
    -0.14
    ãĥ³ãĥij
    -0.14
    ümÃ¼ÅŁ
    -0.14
    رÙĬÙħ
    -0.14
    oningen
    -0.14
    POSITIVE LOGITS
    /security
    0.16
    essel
    0.16
     Aug
    0.15
    oran
    0.15
    elta
    0.14
    lands
    0.14
    ionale
    0.14
    าà¸ĺ
    0.14
    dom
    0.14
    sock
    0.14
    Act Density 0.007%

    No Known Activations