INDEX
    Explanations

    references to terrorist groups and related violent events

    New Auto-Interp
    Negative Logits
    oom
    -0.15
    olest
    -0.15
    agle
    -0.15
    romo
    -0.15
    umen
    -0.14
    inen
    -0.14
    ofs
    -0.14
    ekk
    -0.14
    omen
    -0.14
    notes
    -0.14
    POSITIVE LOGITS
    ophil
    0.16
    adir
    0.16
    adel
    0.15
    nestjs
    0.14
     epid
    0.14
     ê
    0.14
    IService
    0.14
    zdy
    0.14
    íĻĶ
    0.14
     (~(
    0.14
    Act Density 0.004%

    No Known Activations