INDEX
Explanations
mentions of steak or related terms
New Auto-Interp
Negative Logits
inators
-0.69
perse
-0.69
etheless
-0.69
blance
-0.68
Telecommunications
-0.68
umbn
-0.67
Citizens
-0.65
sembly
-0.64
antics
-0.62
ync
-0.62
POSITIVE LOGITS
steak
1.13
fish
0.99
house
0.98
dinners
0.97
knives
0.94
houses
0.92
dinner
0.92
cloth
0.92
balls
0.90
worms
0.86
Activations Density 0.002%