INDEX
Explanations
phrases related to vaccines and vaccination status
New Auto-Interp
Negative Logits
oyo
-0.15
esus
-0.15
ague
-0.15
axon
-0.14
ÏĨα
-0.14
iji
-0.13
AppModule
-0.13
asar
-0.13
oor
-0.13
ws
-0.13
POSITIVE LOGITS
ürn
0.15
oplay
0.14
etler
0.14
Hale
0.14
oram
0.14
.IDENTITY
0.14
ibraltar
0.13
Siz
0.13
Sov
0.13
otent
0.13
Activations Density 0.005%