INDEX
Explanations
mentions of the name "Simon" at various positions within text
the occurrences of the name "Simon."
New Auto-Interp
Negative Logits
rake
-0.81
ntil
-0.79
merce
-0.77
ttes
-0.76
roxy
-0.75
awaru
-0.75
ecause
-0.70
addons
-0.70
00200000
-0.69
gypt
-0.69
POSITIVE LOGITS
Says
0.95
etti
0.90
Simon
0.87
zman
0.81
Simon
0.81
stown
0.78
Brav
0.76
itars
0.76
sell
0.74
Gan
0.73
Activations Density 0.016%