INDEX
Explanations
references to the concept of "big" in various contexts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.34
1.6%
1757
+0.13
0.6%
1350
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
481
+0.34
0.06
405
+0.13
0.06
1506
+0.13
0.05
Negative Logits
<bos>
-1.62
<?
-0.69
/*
-0.63
bigsqcup
-0.63
triangleq
-0.62
-0.61
<tfoot>
-0.57
koc
-0.57
textnormal
-0.57
xymatrix
-0.54
POSITIVE LOGITS
big
1.20
BIG
1.13
big
1.08
Big
1.02
BIG
1.01
Big
0.98
Biggs
0.91
Bigelow
0.86
impractica
0.86
viciss
0.82
Activations Density 0.112%