INDEX
Explanations
occurrences of the word "testing."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
156
+0.16
0.9%
376
+0.16
0.9%
443
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
484
+0.16
0.02
14
+0.16
0.02
443
+0.10
0.02
Negative Logits
Ļª
-2.49
§
-2.42
¯
-2.35
IJ
-2.31
Ĵ
-2.28
Ĺ
-2.19
ij
-2.15
Ŀ
-1.98
ı
-1.95
ĸ
-1.95
POSITIVE LOGITS
crop
1.88
instrument
1.81
bird
1.79
birds
1.77
apparatus
1.68
aments
1.65
instruments
1.62
sticks
1.57
styles
1.57
area
1.56
Activations Density 0.104%