INDEX
    Explanations

    mentions of notable individuals' deaths

    New Auto-Interp
    Negative Logits
     ul
    -0.16
    705
    -0.15
    tura
    -0.15
    onth
    -0.15
    apur
    -0.14
     likes
    -0.14
     rat
    -0.14
    gps
    -0.14
     existing
    -0.14
     geo
    -0.13
    POSITIVE LOGITS
    orest
    0.17
    endet
    0.16
    GuidId
    0.16
    вÑģÑı
    0.15
     aged
    0.15
    iParam
    0.14
    stal
    0.14
    isay
    0.14
     возÑĢаÑģÑĤ
    0.14
    wers
    0.14
    Act Density 0.037%

    No Known Activations