INDEX
Explanations
references to infectious diseases and their impacts
New Auto-Interp
Negative Logits
ä¿
-0.16
Dough
-0.16
ergus
-0.16
stroy
-0.16
esium
-0.15
ptom
-0.15
addCriterion
-0.15
inese
-0.15
chedulers
-0.15
iglia
-0.15
POSITIVE LOGITS
Tub
0.33
ty
0.30
Deng
0.30
rab
0.29
TB
0.29
tuberculosis
0.28
communic
0.28
TB
0.27
Ty
0.26
Anth
0.25
Activations Density 0.254%