INDEX
Explanations
words associated with intelligence and cleverness
New Auto-Interp
Negative Logits
977
-0.15
CHASE
-0.14
ẻ
-0.14
specifier
-0.13
tant
-0.13
ORB
-0.13
etsk
-0.13
breaking
-0.13
entr
-0.13
geber
-0.13
POSITIVE LOGITS
ilo
0.15
oul
0.14
icken
0.14
IQ
0.14
ivi
0.14
insights
0.13
&T
0.13
оÑĤв
0.13
ddf
0.13
eda
0.13
Activations Density 0.098%