INDEX
Explanations
words related to the concept of "bore" or boredom
New Auto-Interp
Negative Logits
%"
-0.68
ournal
-0.67
%]
-0.66
ILCS
-0.66
Phoenix
-0.65
Hots
-0.65
é¾įå
-0.64
afort
-0.63
pired
-0.62
Republic
-0.62
POSITIVE LOGITS
tto
1.00
tta
0.98
alis
0.98
hole
0.94
holes
0.93
ttes
0.91
ller
0.88
vest
0.85
lli
0.85
lla
0.85
Activations Density 0.005%