INDEX
    Explanations

    mentions of colors, particularly variations of blue and related terminology

    New Auto-Interp
    Negative Logits
    Personensuche
    -1.02
     ComVisible
    -0.87
     Roskov
    -0.84
     Normdatei
    -0.83
     propOrder
    -0.82
    NameInMap
    -0.77
     ostavi
    -0.74
    lihood
    -0.73
     OMITBAD
    -0.73
    sizeCache
    -0.71
    POSITIVE LOGITS
     haired
    0.49
    wal
    0.47
    くれない
    0.45
    hagic
    0.45
     renkli
    0.45
     colored
    0.45
     smoke
    0.45
    bor
    0.43
    mar
    0.43
     boto
    0.43
    Act Density 0.185%

    No Known Activations