INDEX
    Explanations

    mentions of casualties and injuries in various contexts

    New Auto-Interp
    Negative Logits
    ouser
    -0.15
    zie
    -0.14
    sted
    -0.14
    _Invoke
    -0.14
     kav
    -0.14
     Î
    -0.14
    ková
    -0.13
    озÑı
    -0.13
    gne
    -0.13
    à¥Ģद
    -0.13
    POSITIVE LOGITS
    127
    0.15
    asser
    0.14
    desk
    0.14
    ë§Į
    0.13
    anvas
    0.13
    }@
    0.13
     Nik
    0.13
    723
    0.13
    aml
    0.13
     близ
    0.13
    Act Density 0.018%

    No Known Activations