INDEX
    Explanations

    references to engraving and printmaking techniques

    New Auto-Interp
    Negative Logits
     Morr
    -0.17
    olson
    -0.17
     Photography
    -0.16
     photographed
    -0.16
     photography
    -0.16
    _photos
    -0.15
     photographs
    -0.15
    ennes
    -0.15
     breakout
    -0.14
    edores
    -0.14
    POSITIVE LOGITS
     print
    0.27
     printing
    0.26
     prints
    0.24
    print
    0.23
     Print
    0.20
    printing
    0.20
    -print
    0.20
     printers
    0.20
     printer
    0.20
     Printing
    0.20
    Act Density 0.056%

    No Known Activations