INDEX
    Explanations

    references to multicultural and interracial themes or identities

    New Auto-Interp
    Negative Logits
    -0.21
    that
    -0.19
    but
    -0.18
    this
    -0.18
    it
    -0.18
    inde
    -0.17
    the
    -0.17
     that
    -0.17
    .
    -0.17
    -P
    -0.17
    POSITIVE LOGITS
     unpublished
    0.25
     formerly
    0.24
     eds
    0.23
     accessed
    0.21
     ed
    0.21
     dir
    0.20
     originally
    0.20
     unknown
    0.20
     edited
    0.20
     retrieved
    0.19
    Act Density 0.485%

    No Known Activations