INDEX
Explanations
phrases related to economic hardship and poverty
New Auto-Interp
Negative Logits
immune
-0.15
pute
-0.15
Æ°á»Ľng
-0.14
ivÄĽ
-0.14
.timeScale
-0.14
kuru
-0.13
èŃ
-0.13
uzzi
-0.13
zzo
-0.13
guard
-0.13
POSITIVE LOGITS
poverty
0.23
-po
0.22
prec
0.22
below
0.21
Poverty
0.20
sub
0.20
Prec
0.19
Cycle
0.18
cycle
0.18
cycles
0.18
Activations Density 0.072%