INDEX
Explanations
mentions of the name "Murray"
New Auto-Interp
Negative Logits
iaries
-0.78
ulatory
-0.74
ulation
-0.71
--------------------------------------------------------
-0.69
reek
-0.68
skelet
-0.68
ened
-0.68
graded
-0.68
umper
-0.68
apache
-0.68
POSITIVE LOGITS
cliffe
0.74
hoe
0.74
wald
0.72
cloth
0.70
Bros
0.70
hyde
0.69
vill
0.68
stein
0.68
anyahu
0.67
zeb
0.67
Activations Density 0.024%