INDEX
Explanations
variations of the verb "turn."
New Auto-Interp
Negative Logits
apo
-0.17
UBL
-0.17
ifice
-0.16
frei
-0.16
oop
-0.16
gt
-0.15
abase
-0.15
../../../
-0.14
otes
-0.14
uhn
-0.14
POSITIVE LOGITS
pike
0.21
stile
0.17
ipse
0.16
ero
0.15
ovan
0.14
anking
0.14
unci
0.14
chatte
0.14
ismo
0.14
outs
0.14
Activations Density 0.054%