INDEX
    Explanations

    references to alumni of specific high schools

    New Auto-Interp
    Negative Logits
    folk
    -0.17
     transformer
    -0.17
    uder
    -0.15
    olars
    -0.14
    peat
    -0.14
    olar
    -0.14
    fol
    -0.13
     Transformer
    -0.13
    347
    -0.13
    =$('#
    -0.13
    POSITIVE LOGITS
    aversable
    0.15
     Snow
    0.15
    inka
    0.15
     snow
    0.14
    admins
    0.14
    andest
    0.14
    ุà¹ī
    0.14
    çĵľ
    0.14
     Roberts
    0.14
    à¹ĥà¸Ī
    0.13
    Act Density 0.003%

    No Known Activations