INDEX
Explanations
words related to physical discomfort or pain
instances of the substring "gh" in various contexts
New Auto-Interp
Negative Logits
closest
-0.72
Bots
-0.71
satell
-0.70
cort
-0.68
stewards
-0.65
nesday
-0.65
prosec
-0.65
Purg
-0.63
bapt
-0.63
Draper
-0.62
POSITIVE LOGITS
gh
1.06
ttp
1.02
mt
0.98
orns
0.93
awk
0.91
hhhh
0.90
doms
0.84
ouse
0.84
ouls
0.84
orse
0.82
Activations Density 0.007%