INDEX
Explanations
proper nouns
occurrences of the name "Murphy"
New Auto-Interp
Negative Logits
arers
-0.78
iary
-0.78
eking
-0.76
ential
-0.71
Chandra
-0.68
onent
-0.68
naires
-0.67
andr
-0.67
Cf
-0.66
arer
-0.65
POSITIVE LOGITS
ufact
0.90
igans
0.79
Murphy
0.78
lich
0.67
der
0.67
rats
0.64
ascus
0.64
wallet
0.62
Cloak
0.62
Collins
0.61
Activations Density 0.007%