INDEX
    Explanations

    mentions of healthcare-related issues and statistics

    New Auto-Interp
    Negative Logits
    inkle
    -0.19
     incel
    -0.17
    ÙĦÙĬÙĩ
    -0.15
    /Instruction
    -0.14
     Ekim
    -0.14
     vet
    -0.14
    EO
    -0.14
     mắt
    -0.14
     tort
    -0.14
    ein
    -0.14
    POSITIVE LOGITS
     HIV
    0.54
     AIDS
    0.47
    /AIDS
    0.32
     gay
    0.27
     Retro
    0.24
     viral
    0.23
    gay
    0.21
     retro
    0.21
    Gay
    0.21
     Gay
    0.21
    Act Density 0.053%

    No Known Activations