INDEX
Explanations
specific nouns and objects related to environmental and health contexts
New Auto-Interp
Negative Logits
atti
-0.16
argent
-0.15
@student
-0.14
ester
-0.14
idel
-0.14
uars
-0.14
Associated
-0.14
Wolff
-0.14
,LOCATION
-0.14
arseille
-0.13
POSITIVE LOGITS
è
0.19
Ptr
0.16
ior
0.15
yo
0.15
623
0.15
Innoc
0.14
iod
0.14
720
0.14
976
0.14
ican
0.14
Activations Density 0.009%