INDEX
Explanations
mentions of committees and committee-related activities
New Auto-Interp
Negative Logits
çĦ¶
-0.18
rahim
-0.16
ashi
-0.16
/sm
-0.15
leta
-0.15
edm
-0.15
coming
-0.14
sn
-0.14
het
-0.14
script
-0.14
POSITIVE LOGITS
tees
0.25
tee
0.21
ters
0.18
uzzle
0.16
ä»¶
0.16
artment
0.16
ting
0.15
aux
0.15
\HttpFoundation
0.15
members
0.15
Activations Density 0.016%