INDEX
Explanations
mentions of medical or health-related terms, specifically those related to asthma and its management
New Auto-Interp
Negative Logits
dap
-0.16
bane
-0.16
b
-0.16
classNames
-0.15
mie
-0.14
det
-0.14
arkin
-0.14
dar
-0.14
id
-0.14
Suche
-0.14
POSITIVE LOGITS
yntax
0.17
holder
0.16
rica
0.15
cies
0.15
Ńå·ŀ
0.15
afen
0.14
able
0.14
night
0.14
uffle
0.14
adesh
0.14
Activations Density 0.012%