INDEX
Explanations
phrases related to prestigious or exceptional entities
New Auto-Interp
Negative Logits
obiles
-0.71
Rapp
-0.64
ABE
-0.63
nery
-0.63
edia
-0.63
OTOS
-0.62
Fired
-0.62
Apocalypse
-0.61
ARP
-0.61
Tactics
-0.61
POSITIVE LOGITS
jewel
1.22
jewels
1.20
pin
1.04
prince
1.01
pins
0.95
doms
0.88
fal
0.84
ingen
0.81
crown
0.80
stroke
0.80
Activations Density 0.016%