INDEX
    Explanations

    mentions of violent events and legal actions

    phrases related to criminal activities and violent events

    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.66
    )."
    -0.63
    -)
    -0.62
    \)
    -0.60
     respons
    -0.60
    pled
    -0.59
     looph
    -0.58
     incorpor
    -0.58
     pse
    -0.57
    anan
    -0.56
    POSITIVE LOGITS
    utterstock
    0.86
     Belfast
    0.86
    AFP
    0.71
    ONDON
    0.68
     Wednesday
    0.68
     Copyright
    0.67
     Narendra
    0.66
     Transgender
    0.66
     Posted
    0.66
     Thursday
    0.65
    Act Density 1.036%

    No Known Activations