INDEX
Explanations
references to governmental roles, actions, and decisions
New Auto-Interp
Negative Logits
spir
-0.17
Viewer
-0.15
arga
-0.15
ÃŁ
-0.15
Spir
-0.14
spir
-0.14
_viewer
-0.14
вад
-0.14
ten
-0.14
echa
-0.14
POSITIVE LOGITS
Cabinet
0.17
ipped
0.15
iali
0.14
)init
0.14
hton
0.14
nis
0.14
_zeros
0.14
ially
0.14
ild
0.14
Thom
0.14
Activations Density 0.103%