INDEX
Explanations
references to graphic design
New Auto-Interp
Negative Logits
yr
-0.17
ym
-0.17
geb
-0.16
iro
-0.16
wick
-0.15
uction
-0.15
ismic
-0.15
extr
-0.15
oy
-0.15
yt
-0.15
POSITIVE LOGITS
designer
0.22
novels
0.21
novel
0.20
arts
0.20
designers
0.19
Novel
0.19
ENE
0.19
-intensive
0.18
Designer
0.18
-design
0.18
Activations Density 0.010%