INDEX
Explanations
terms related to innovation and creativity
New Auto-Interp
Negative Logits
abouts
-0.17
Zuk
-0.16
dater
-0.15
pherd
-0.15
olie
-0.15
loid
-0.15
eo
-0.15
ownt
-0.15
orian
-0.14
odied
-0.14
POSITIVE LOGITS
ideas
0.19
aries
0.18
/new
0.18
/original
0.17
spirit
0.16
hub
0.15
Hub
0.15
-Mar
0.14
ary
0.14
hub
0.14
Activations Density 0.017%