INDEX
    Explanations

    mentions of disease or health-related hazards

    New Auto-Interp
    Negative Logits
    [
    -0.16
    ennen
    -0.16
    -0.16
    `
    -0.15
     
    -0.15
    y
    -0.15
    "
    -0.15
    â̦
    -0.15
    Âł
    -0.15
    ,
    -0.14
    POSITIVE LOGITS
    _exempt
    0.17
     [â̦]↵↵
    0.15
    AFX
    0.15
    .onViewCreated
    0.15
     Dün
    0.14
    ITIZE
    0.14
    nore
    0.14
    çĤī
    0.14
     lục
    0.14
    лÑĸд
    0.14
    Act Density 0.257%

    No Known Activations