INDEX
Explanations
references to visual artworks and their creators
New Auto-Interp
Negative Logits
Instrument
-0.16
Instrument
-0.16
avana
-0.15
ez
-0.15
axe
-0.14
cuckold
-0.14
codegen
-0.14
Oculus
-0.14
Map
-0.14
.pth
-0.14
POSITIVE LOGITS
Andy
0.38
Factory
0.33
War
0.33
Andy
0.30
Campbell
0.27
Pop
0.27
Factory
0.26
pop
0.26
sil
0.25
Pop
0.24
Activations Density 0.009%