INDEX
Explanations
terms related to environmental issues and health impacts
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
369
+0.16
0.9%
47
+0.16
0.9%
320
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
487
+0.16
0.03
143
+0.16
0.03
66
+0.13
0.05
Negative Logits
scratch
-1.73
</
-1.73
registry
-1.62
(<
-1.61
www
-1.58
batim
-1.57
interface
-1.56
vier
-1.53
*.
-1.49
sites
-1.49
POSITIVE LOGITS
į
2.43
ĭ
2.41
ĻĤ
2.29
Ļª
2.21
ĥ
2.20
º
2.11
Ŀ
2.09
ĩ
2.06
ħ
2.00
Ĩ
1.99
Activations Density 0.745%