INDEX
Explanations
names of people or characters
New Auto-Interp
Negative Logits
emu
-0.18
íıī
-0.15
anga
-0.15
embro
-0.14
.Prot
-0.14
estr
-0.14
odom
-0.14
ainter
-0.14
FAG
-0.14
atom
-0.14
POSITIVE LOGITS
akes
0.17
453
0.16
Cool
0.15
Lun
0.15
983
0.15
188
0.15
132
0.14
ãĥªãĤ«
0.14
coolest
0.14
871
0.14
Activations Density 0.078%