INDEX
Explanations
the word "parliament" or related terms
references to legislative bodies or parliamentary systems
New Auto-Interp
Negative Logits
ept
-0.70
imilar
-0.62
ãģŁ
-0.61
uber
-0.60
tex
-0.60
CONT
-0.59
ãģ¦
-0.59
BOOK
-0.59
TRUMP
-0.59
jiang
-0.59
POSITIVE LOGITS
arians
1.37
arian
1.06
liament
0.93
ional
0.87
Speaker
0.87
parliament
0.84
acus
0.83
recess
0.80
bourg
0.79
lain
0.77
Activations Density 0.015%