INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Changes
    -0.08
    555
    -0.07
    52
    -0.07
    git
    -0.07
    (Debug
    -0.07
     elusive
    -0.07
    _re
    -0.07
     loca
    -0.07
     municipalities
    -0.07
    -0.07
    POSITIVE LOGITS
     hateful
    0.11
     hatred
    0.10
     공격
    0.10
     haine
    0.10
     violence
    0.09
     fuels
    0.09
    0.09
     ആക്രമ
    0.09
     Oromoo
    0.09
     extremist
    0.09
    Act Density 0.005%

    No Known Activations