INDEX
Explanations
mentions of the name "Guy" in various contexts
New Auto-Interp
Negative Logits
alley
-0.17
reu
-0.17
aries
-0.17
rik
-0.16
hower
-0.15
defaultCenter
-0.15
berg
-0.15
utzer
-0.15
ÑģÑĥÑĤ
-0.15
ussen
-0.14
POSITIVE LOGITS
ana
0.19
friend
0.18
riend
0.18
brush
0.17
anan
0.17
dra
0.16
Friend
0.16
/g
0.16
atri
0.15
dire
0.15
Activations Density 0.006%