INDEX
Explanations
words related to envy and competition
New Auto-Interp
Negative Logits
plane
-0.15
Plane
-0.15
ulum
-0.14
ufact
-0.14
forwards
-0.14
Modify
-0.14
awe
-0.14
itag
-0.14
uli
-0.14
Plane
-0.14
POSITIVE LOGITS
obel
0.16
ridge
0.15
631
0.15
SSERT
0.15
озÑĸ
0.14
0.14
544
0.14
溪
0.13
ắc
0.13
ofire
0.13
Activations Density 0.354%