INDEX
Explanations
descriptions of artwork and artistic elements
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.24
0.8%
184
+0.16
0.5%
453
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
184
+0.24
0.02
453
+0.16
0.05
1419
+0.15
0.03
Negative Logits
unlaw
-1.03
unspeak
-1.00
pamph
-0.99
apprehen
-0.95
philanth
-0.92
Yugos
-0.90
indescri
-0.88
sophistic
-0.88
EEU
-0.88
intrigu
-0.87
POSITIVE LOGITS
<bos>
0.88
+#+
0.59
but
0.58
cliquez
0.53
Offisielt
0.52
;,
0.52
الحره
0.52
Leider
0.51
Palmar
0.50
imanapun
0.50
Activations Density 0.434%