INDEX
Explanations
phrases that denote the act of creation
New Auto-Interp
Negative Logits
minor
-0.15
blink
-0.15
iban
-0.15
AbsolutePath
-0.15
weeney
-0.14
pot
-0.14
relative
-0.14
ivate
-0.14
UIG
-0.14
twice
-0.14
POSITIVE LOGITS
cona
0.16
ulos
0.15
sis
0.15
iona
0.15
SEE
0.14
476
0.14
uby
0.14
пи
0.14
.swt
0.14
engo
0.14
Activations Density 0.022%