INDEX
Explanations
concepts related to societal critique and historical reflections on capitalism and power dynamics
New Auto-Interp
Negative Logits
quete
-0.20
ntax
-0.15
celain
-0.15
Ã¥n
-0.15
erview
-0.14
нг
-0.14
spare
-0.14
Göz
-0.14
ichtig
-0.14
narr
-0.13
POSITIVE LOGITS
relevance
0.36
relev
0.30
relevant
0.25
today
0.25
applicable
0.25
applic
0.25
timeless
0.24
акÑĤÑĥ
0.24
relevant
0.23
ä»Ĭ天
0.23
Activations Density 0.225%