INDEX
    Explanations

    references to disabilities, particularly cerebral palsy

    New Auto-Interp
    Negative Logits
    Ł
    -0.17
    ãģıãĤĮãģŁ
    -0.17
    zhou
    -0.15
    ÙĬÙĦا
    -0.14
    Ell
    -0.14
    WindowText
    -0.14
    ãĥĨãĥ«
    -0.14
     Edison
    -0.14
    fst
    -0.14
    ISED
    -0.14
    POSITIVE LOGITS
    gs
    0.18
    ach
    0.17
    ack
    0.17
     Pai
    0.17
    omal
    0.16
    ox
    0.15
    emmel
    0.15
    ±
    0.15
    gh
    0.15
    gb
    0.15
    Act Density 0.038%

    No Known Activations