INDEX
Explanations
mentions of different types and characteristics of cheese
New Auto-Interp
Negative Logits
otr
-0.18
nings
-0.15
e
-0.15
ept
-0.15
ures
-0.14
ESC
-0.14
-minded
-0.14
igen
-0.14
abr
-0.14
odega
-0.14
POSITIVE LOGITS
burger
0.32
burg
0.26
fond
0.20
balls
0.19
quake
0.19
board
0.18
Fon
0.18
wheel
0.17
ball
0.17
бÑĥÑĢг
0.17
Activations Density 0.007%