INDEX
Explanations
references to historical or artistic context in creative works
New Auto-Interp
Negative Logits
653
-0.15
osci
-0.14
angl
-0.14
Fare
-0.14
amac
-0.13
NG
-0.13
nton
-0.13
vo
-0.13
726
-0.13
Gone
-0.13
POSITIVE LOGITS
TRANSFER
0.18
δά
0.17
ĶåĽŀ
0.16
hence
0.16
transfer
0.15
Transfer
0.15
original
0.15
uitka
0.15
æĬľ
0.15
originally
0.15
Activations Density 0.184%