INDEX
Explanations
items that are crafted or manufactured, highlighting processes of creation and production
New Auto-Interp
Negative Logits
als
-0.16
ude
-0.15
isse
-0.15
wit
-0.14
storybook
-0.14
cent
-0.14
mares
-0.14
atic
-0.14
pon
-0.14
seo
-0.14
POSITIVE LOGITS
entirely
0.21
with
0.19
made
0.18
withd
0.18
out
0.17
made
0.17
Made
0.17
using
0.16
olland
0.16
according
0.16
Activations Density 0.037%