INDEX
Explanations
references to Congress and legislative activities
New Auto-Interp
Negative Logits
utut
-0.17
ÅĽmy
-0.16
tant
-0.15
.infinity
-0.15
uku
-0.15
lej
-0.15
requently
-0.14
веÑĢж
-0.14
tdown
-0.14
appa
-0.14
POSITIVE LOGITS
/world
0.16
opher
0.15
Glover
0.14
-wide
0.14
ãĥ¼ãĥª
0.14
elijk
0.14
arie
0.14
itable
0.13
ãĥĥãĥģ
0.13
ional
0.13
Activations Density 0.016%