INDEX
    Explanations

    mentions of medical conditions and health-related issues

    New Auto-Interp
    Negative Logits
    ÅĻet
    -0.19
    åĨµ
    -0.14
    Labels
    -0.14
    éϵ
    -0.14
    arda
    -0.14
     baise
    -0.14
    üzel
    -0.14
    peÄį
    -0.14
    uien
    -0.13
    ------------------------------------------------------------------------------------------------
    -0.13
    POSITIVE LOGITS
     Welcome
    0.28
    Welcome
    0.27
     welcome
    0.26
     home
    0.23
    elcome
    0.20
    Home
    0.20
    welcome
    0.19
    About
    0.19
     Home
    0.19
     Founded
    0.18
    Act Density 0.465%

    No Known Activations