INDEX
Explanations
references to a specific individual, likely an artist, within the text
New Auto-Interp
Negative Logits
uality
-0.17
iard
-0.16
mouth
-0.15
aller
-0.15
cancelButtonTitle
-0.14
ÙĦÙĦ
-0.14
fty
-0.14
ivity
-0.14
kou
-0.14
yar
-0.14
POSITIVE LOGITS
rub
0.22
Rub
0.20
instein
0.19
rics
0.19
bing
0.18
ocop
0.17
ellite
0.17
rub
0.17
rubbed
0.17
elbows
0.16
Activations Density 0.013%