INDEX
Explanations
references to political positions or titles related to assembly members
New Auto-Interp
Negative Logits
CONST
-0.16
piel
-0.15
CEO
-0.15
soc
-0.14
lander
-0.14
ÑĤÑĢи
-0.14
pais
-0.14
riel
-0.14
alian
-0.14
Hitch
-0.13
POSITIVE LOGITS
uhan
0.15
RuleContext
0.15
Ñij
0.15
peaker
0.15
istory
0.14
uest
0.14
Äijá»ģ
0.14
MLA
0.14
yle
0.14
ford
0.14
Activations Density 0.026%