INDEX
Explanations
instances of the word "position."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
115
+0.15
0.9%
31
+0.11
0.6%
172
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
31
+0.15
0.01
66
+0.11
0.01
465
+0.10
0.01
Negative Logits
ķ
-2.22
ĩ
-2.15
²
-2.14
ĥ½
-2.12
Ī
-2.08
»¿
-2.02
»
-1.98
½
-1.94
³
-1.93
?’
-1.91
POSITIVE LOGITS
ary
2.08
al
2.06
naire
2.00
erior
1.99
alent
1.98
istical
1.78
ist
1.77
ive
1.72
heses
1.71
ional
1.65
Activations Density 0.027%