INDEX
    Explanations

    references to sports teams and their players, particularly focusing on statistics and roster details

    New Auto-Interp
    Negative Logits
    eref
    -0.17
    ãĥ³ãĥIJ
    -0.17
    oger
    -0.15
    .scalablytyped
    -0.15
    caller
    -0.14
    vention
    -0.14
    cestor
    -0.14
    fcn
    -0.14
    éŃĤ
    -0.14
    queen
    -0.13
    POSITIVE LOGITS
     whose
    0.20
    whose
    0.17
    772
    0.16
     active
    0.16
     whom
    0.15
     who
    0.15
     familiar
    0.15
    RS
    0.14
     pier
    0.14
     key
    0.14
    Act Density 0.130%

    No Known Activations