INDEX
    Explanations

    proper nouns, particularly names of people

    New Auto-Interp
    Negative Logits
    yc
    -0.14
    "]==
    -0.14
    ish
    -0.14
     Sno
    -0.14
     Clo
    -0.14
    ukan
    -0.14
     ImmutableList
    -0.14
    anc
    -0.14
    anda
    -0.13
    ú
    -0.13
    POSITIVE LOGITS
     ayrıca
    0.19
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.17
    iag
    0.16
    ÅĻez
    0.15
    okrat
    0.15
    _unicode
    0.14
    θα
    0.14
    νÏİ
    0.14
    ازÙĦ
    0.14
    EDGE
    0.14
    Act Density 0.126%

    No Known Activations