INDEX
    Explanations

    references to military organizations and their training or activities

    New Auto-Interp
    Negative Logits
    incy
    -0.15
    stad
    -0.15
    rief
    -0.15
    roken
    -0.14
    ahren
    -0.14
    stadt
    -0.14
     Rolls
    -0.14
    isel
    -0.14
     Morm
    -0.14
     invasion
    -0.14
    POSITIVE LOGITS
     training
    0.16
     aid
    0.15
    gett
    0.15
     radical
    0.15
     al
    0.14
     pros
    0.14
     networks
    0.14
    .rar
    0.14
     contacts
    0.14
    etur
    0.14
    Act Density 0.027%

    No Known Activations