INDEX
Explanations
themes related to totalitarianism and oppression
New Auto-Interp
Negative Logits
ä»Ĭå¹´
-0.16
ì°°
-0.15
dao
-0.14
EndElement
-0.14
zell
-0.14
åĬ
-0.14
Serious
-0.14
averse
-0.14
CAA
-0.13
misunderstood
-0.13
POSITIVE LOGITS
society
0.17
Society
0.14
ummings
0.14
azzi
0.13
kB
0.13
congress
0.13
980
0.13
indent
0.13
جاد
0.13
HomePage
0.13
Activations Density 0.103%