INDEX
Explanations
references to solo musical performances or solo artists
New Auto-Interp
Negative Logits
alet
-0.18
reb
-0.17
agar
-0.15
erli
-0.15
rik
-0.15
akedown
-0.14
ESS
-0.14
Gors
-0.14
pen
-0.14
ba
-0.14
POSITIVE LOGITS
/single
0.23
ists
0.23
/group
0.23
baÅŁÄ±na
0.19
/small
0.17
istic
0.17
andel
0.16
ISTS
0.16
istically
0.15
oman
0.15
Activations Density 0.007%