INDEX
Explanations
lines of code or programming constructs related to functions and their parameters
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
317
+0.12
0.7%
468
+0.12
0.7%
185
+0.11
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
53
+0.12
0.11
468
+0.12
0.10
119
+0.11
0.07
Negative Logits
«
-4.81
¢
-4.59
Īĺ
-4.47
½
-4.46
Ĭ
-4.42
ģ
-4.38
¨
-4.36
Į
-4.35
ij
-4.35
IJ
-4.34
POSITIVE LOGITS
"}](#
1.60
=>
1.57
substack
1.50
---|---
1.48
abroad
1.38
amsfonts
1.36
~~~
1.36
license
1.33
bp
1.32
includes
1.28
Activations Density 0.645%