INDEX
Explanations
references to Congress and legislative actions
New Auto-Interp
Negative Logits
appa
-0.16
uku
-0.16
utut
-0.15
requently
-0.15
unga
-0.14
age
-0.14
lej
-0.13
_globals
-0.13
standen
-0.13
etes
-0.13
POSITIVE LOGITS
reesome
0.15
à¸´à¸Ľ
0.15
HEME
0.14
opher
0.14
.***.***
0.14
Glover
0.14
.synthetic
0.14
ÏĮÏģ
0.14
addon
0.13
aliz
0.13
Activations Density 0.019%