INDEX
Explanations
words related to science and scientific concepts
New Auto-Interp
Negative Logits
deaux
-0.18
urent
-0.17
coes
-0.16
tyard
-0.16
antine
-0.15
ationally
-0.15
asley
-0.15
ennes
-0.15
theid
-0.15
alem
-0.15
POSITIVE LOGITS
ific
0.42
IFIC
0.33
ÃŃf
0.28
ifik
0.28
ifique
0.27
ifica
0.25
ifi
0.25
fic
0.25
ometrics
0.23
ifice
0.22
Activations Density 0.014%