INDEX
Explanations
terms related to government and political authority
New Auto-Interp
Negative Logits
apl
-0.07
IBE
-0.06
buat
-0.06
ogn
-0.06
272
-0.06
ï¼İ
-0.06
cause
-0.06
ungen
-0.06
adle
-0.05
ALS
-0.05
POSITIVE LOGITS
recently
0.17
last
0.15
yesterday
0.15
earlier
0.14
lately
0.13
recent
0.13
Recently
0.12
Recently
0.11
previously
0.11
recent
0.10
Activations Density 0.053%