INDEX
Explanations
references to genius and brilliance in various contexts
New Auto-Interp
Negative Logits
antine
-0.16
gp
-0.15
fare
-0.15
Ear
-0.15
sak
-0.14
é½
-0.14
aleza
-0.14
Barg
-0.14
olson
-0.14
ente
-0.14
POSITIVE LOGITS
owl
0.17
ubb
0.15
ledi
0.15
uro
0.15
/ext
0.14
olib
0.14
Forrest
0.14
odv
0.14
ushi
0.14
iffer
0.14
Activations Density 0.076%