INDEX
Explanations
mentions of the name "Kevin."
New Auto-Interp
Negative Logits
ied
-0.17
APS
-0.15
aghetti
-0.15
alah
-0.15
itia
-0.14
etine
-0.14
AtPath
-0.14
еÑĢÑĪ
-0.14
rz
-0.14
alars
-0.14
POSITIVE LOGITS
Bacon
0.18
inspace
0.17
Kevin
0.16
Space
0.16
ities
0.16
burg
0.16
Clash
0.15
ism
0.15
Abstract
0.15
rest
0.15
Activations Density 0.006%