INDEX
Explanations
terms that describe ease or speed in processes and tasks
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
128
+0.12
0.7%
370
+0.11
0.6%
297
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
452
+0.12
0.04
338
+0.11
0.04
297
+0.10
0.04
Negative Logits
¼
-3.78
»¿
-3.68
Ī
-3.56
·¸
-3.54
Į
-3.52
¹
-3.46
¬
-3.39
Ĩ
-3.38
º
-3.38
ĸ
-3.32
POSITIVE LOGITS
than
4.05
Than
3.48
than
3.11
Than
3.11
wagen
1.62
ight
1.55
stance
1.53
lifetime
1.49
garten
1.47
?:
1.39
Activations Density 0.222%