INDEX
Explanations
numerical data, particularly dates and statistics
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
157
+0.17
1.0%
459
+0.16
0.9%
17
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
157
+0.17
0.04
452
+0.16
0.01
231
+0.12
0.03
Negative Logits
omed
-1.65
oming
-1.61
oken
-1.61
ancel
-1.55
tered
-1.52
fully
-1.50
discussions
-1.47
ioned
-1.47
figures
-1.40
ered
-1.39
POSITIVE LOGITS
ĥ½
4.38
Ĵ
4.25
µ
4.19
·
4.10
¶
4.10
ij
4.06
ĻĤ
4.02
Ĺ
3.90
ĸ
3.89
²
3.75
Activations Density 0.258%