INDEX
Explanations
terms related to economic theories and ideologies
New Auto-Interp
Negative Logits
Pest
-0.16
anke
-0.15
esh
-0.15
صÙĨ
-0.15
//!<
-0.14
estroy
-0.14
ein
-0.14
rol
-0.14
ivable
-0.14
suz
-0.13
POSITIVE LOGITS
ism
0.23
ist
0.18
apy
0.18
atism
0.16
apist
0.16
ists
0.16
ascus
0.14
주ìĿĺ
0.13
ISM
0.13
alist
0.13
Activations Density 0.096%