INDEX
    Explanations

    references to jihad-related topics

    New Auto-Interp
    Negative Logits
    ality
    -0.17
    æĦıè§ģ
    -0.16
    olley
    -0.16
    alled
    -0.16
    sass
    -0.14
     Aires
    -0.14
    欲
    -0.14
    anja
    -0.14
    اتÙĩ
    -0.14
    HIR
    -0.14
    POSITIVE LOGITS
    -era
    0.18
     fighters
    0.17
    fighters
    0.17
    turnstile
    0.16
     Fighters
    0.16
    ฺ
    0.16
    istant
    0.16
    zsche
    0.16
    \grid
    0.15
    ists
    0.15
    Act Density 0.008%

    No Known Activations