INDEX
Explanations
expressions of creativity and artistic expression
New Auto-Interp
Negative Logits
olest
-0.15
udge
-0.15
ritz
-0.15
cae
-0.14
agna
-0.14
oui
-0.14
rit
-0.14
olas
-0.14
231
-0.14
osaur
-0.14
POSITIVE LOGITS
forth
0.25
ToFront
0.23
Bring
0.22
Bring
0.22
bringing
0.21
into
0.21
bring
0.20
Bringing
0.20
bringing
0.20
Into
0.20
Activations Density 0.066%