INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     violence
    0.65
    Violence
    0.64
     violência
    0.62
     Violence
    0.58
     violencia
    0.56
     traumat
    0.55
    violence
    0.54
     violent
    0.51
    Injury
    0.51
     victim
    0.50
    POSITIVE LOGITS
     богат
    0.48
     товары
    0.47
     arrested
    0.47
    0.46
     ताब्यात
    0.44
    ÜR
    0.43
    ємо
    0.43
     pouches
    0.42
    我們要
    0.42
     bagged
    0.42
    Act Density 0.089%

    No Known Activations