INDEX
    Explanations

    references to gun violence and related incidents

    New Auto-Interp
    Negative Logits
    aign
    -0.17
    irma
    -0.15
    wick
    -0.14
    еÑĢÑĸв
    -0.14
    erea
    -0.14
    itou
    -0.13
    duction
    -0.13
    ást
    -0.13
     embargo
    -0.13
    -blind
    -0.13
    POSITIVE LOGITS
     gunman
    0.34
     shooter
    0.33
     rampage
    0.32
     massacre
    0.31
     shooting
    0.28
     shootings
    0.28
     shooters
    0.27
     massac
    0.27
     Shooter
    0.26
     motive
    0.24
    Act Density 0.036%

    No Known Activations