INDEX
Explanations
mathematical expressions and symbols related to equations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
30
+0.12
0.7%
478
+0.12
0.6%
423
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
423
+0.12
0.02
284
+0.12
0.02
30
+0.11
0.01
Negative Logits
myself
-1.62
me
-1.55
apore
-1.49
mine
-1.47
ible
-1.45
quel
-1.44
cion
-1.42
yourself
-1.41
noreply
-1.41
ninger
-1.40
POSITIVE LOGITS
ī
5.62
¾
5.22
Ĩ
5.21
Ļ
5.17
µ
5.14
Ł
5.10
®
5.07
İ
4.92
¶
4.89
ħ
4.85
Activations Density 0.071%