INDEX
Explanations
phrases related to political terms and elections
New Auto-Interp
Negative Logits
ropa
-0.17
TARGET
-0.14
RESSED
-0.14
ressed
-0.13
akes
-0.13
ëħ¼
-0.13
лоп
-0.12
uru
-0.12
chl
-0.12
ØŃر
-0.12
POSITIVE LOGITS
term
0.58
terms
0.52
term
0.44
Term
0.43
terms
0.42
-term
0.41
Term
0.40
Terms
0.40
TERM
0.38
_term
0.38
Activations Density 0.058%