INDEX
Explanations
references to eggs and their various forms or uses
New Auto-Interp
Negative Logits
vore
-0.16
leck
-0.16
oir
-0.15
eer
-0.15
"()
-0.15
hq
-0.15
anism
-0.15
ellig
-0.15
olson
-0.14
Ore
-0.14
POSITIVE LOGITS
egg
0.24
Egg
0.24
egg
0.24
plant
0.23
shell
0.23
Eggs
0.23
Ñıй
0.22
eggs
0.22
yol
0.19
Goose
0.18
Activations Density 0.007%