INDEX
    Explanations

    references to military equipment and artillery

    New Auto-Interp
    Negative Logits
    ikut
    -0.17
    å¹¹
    -0.15
    illin
    -0.14
    .gc
    -0.14
    quette
    -0.14
    rogen
    -0.14
    辦
    -0.14
     cav
    -0.13
    keh
    -0.13
    otropic
    -0.13
    POSITIVE LOGITS
    xml
    0.17
    IMS
    0.15
    imbus
    0.15
    rys
    0.14
    ifar
    0.14
    /browse
    0.14
    PGA
    0.14
    amp
    0.14
    daq
    0.13
    ë¥
    0.13
    Act Density 0.026%

    No Known Activations