INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Scrib
    -0.07
     zapr
    -0.07
     reproduc
    -0.07
     Jest
    -0.07
     Lukas
    -0.07
     JTable
    -0.07
    anion
    -0.07
    -0.07
     Cau
    -0.07
     Clem
    -0.07
    POSITIVE LOGITS
     terrorist
    0.10
     terrorism
    0.09
     violence
    0.08
    crime
    0.08
     malign
    0.08
     атак
    0.07
    0.07
    vict
    0.07
     ആക്രമ
    0.07
     Во
    0.07
    Act Density 0.006%

    No Known Activations