INDEX
    Explanations

    information related to violence and conflict

    New Auto-Interp
    Negative Logits
    oin
    -0.15
    HeaderText
    -0.14
     overhead
    -0.14
    _REGISTRY
    -0.14
    ornings
    -0.13
    abble
    -0.13
    istle
    -0.13
    ouse
    -0.13
     Velvet
    -0.13
    oller
    -0.13
    POSITIVE LOGITS
     Buck
    0.15
    -regexp
    0.14
     ÐĴеÑĢÑħов
    0.14
    rips
    0.14
    ulp
    0.14
    IFI
    0.14
    åĢī
    0.14
    igg
    0.14
    apor
    0.13
    asjon
    0.13
    Act Density 0.145%

    No Known Activations