INDEX
Explanations
titles of songs and their associated artists or details
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
451
+0.12
0.6%
433
+0.12
0.6%
294
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
200
+0.12
0.03
140
+0.12
0.03
67
+0.11
0.01
Negative Logits
:`
-1.77
ier
-1.70
getInstance
-1.53
.[]{-1.52
policy
-1.50
taxpayers
-1.48
essen
-1.48
taxpayer
-1.47
*^
-1.44
ALLOC
-1.39
POSITIVE LOGITS
vocals
2.00
finale
1.90
rhythm
1.89
musical
1.88
louder
1.80
sung
1.79
music
1.78
Comedy
1.77
singing
1.76
narrator
1.69
Activations Density 0.418%