INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     seismic
    -0.08
     adjective
    -0.08
     GBP
    -0.08
     pere
    -0.08
    -0.08
     ply
    -0.08
     rustic
    -0.08
     cumbersome
    -0.08
     pottery
    -0.08
     fluff
    -0.08
    POSITIVE LOGITS
    /AIDS
    0.17
     HIV
    0.13
     AIDS
    0.12
    病毒
    0.11
     deaths
    0.09
     queer
    0.09
    死亡
    0.09
    Deaths
    0.09
     संक्रमित
    0.08
     virus
    0.08
    Act Density 0.005%

    No Known Activations