INDEX
    Explanations

    references to shootings and gun-related incidents

    New Auto-Interp
    Negative Logits
    endir
    -0.20
    orial
    -0.16
    deen
    -0.15
    isex
    -0.15
    sak
    -0.14
    ê¹
    -0.14
    isters
    -0.14
    ifu
    -0.14
    olin
    -0.14
    ãĥ«ãĥĪ
    -0.13
    POSITIVE LOGITS
    aaS
    0.15
     Fields
    0.14
    INVAL
    0.14
    ets
    0.14
    ium
    0.13
    ><![
    0.13
    .browser
    0.13
     åĨ
    0.13
    reek
    0.13
     ÙĨÚ¯
    0.13
    Act Density 0.021%

    No Known Activations