INDEX
Explanations
references to graphic design and associated professions
New Auto-Interp
Negative Logits
graphics
-0.19
graph
-0.17
uction
-0.17
grim
-0.17
graphical
-0.16
uctions
-0.16
_GRAPH
-0.16
-government
-0.16
_graph
-0.15
Graphics
-0.15
POSITIVE LOGITS
novels
0.27
Novel
0.27
novel
0.26
novelist
0.23
arts
0.23
Arts
0.20
-intensive
0.18
Nov
0.18
Nov
0.18
acy
0.18
Activations Density 0.018%