INDEX
Explanations
mentions of the name "Graham"
occurrences of the name "Graham."
New Auto-Interp
Negative Logits
Rated
-0.76
puter
-0.76
————————
-0.72
selves
-0.71
self
-0.67
merce
-0.65
haps
-0.64
âĹ¼
-0.64
Kinnikuman
-0.63
ting
-0.62
POSITIVE LOGITS
Graham
1.10
Graham
0.98
maxwell
0.83
iband
0.77
urus
0.77
Greene
0.76
Hancock
0.76
etti
0.75
essen
0.75
osponsors
0.75
Activations Density 0.006%