INDEX
Explanations
inquiries related to governmental accountability and health statistics
New Auto-Interp
Negative Logits
kus
-0.20
ulling
-0.15
"**
-0.14
nawet
-0.14
subt
-0.14
«
-0.14
utherland
-0.14
Ìī
-0.13
erais
-0.13
.synthetic
-0.13
POSITIVE LOGITS
azon
0.17
rawer
0.17
anni
0.17
stadt
0.16
)':
0.15
λλα
0.14
ÑĥÑĢÑĥ
0.14
ÃĽ
0.14
kea
0.14
boz
0.14
Activations Density 0.002%