INDEX
Explanations
terms related to medical classifications and coding systems
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
371
+0.11
0.6%
202
+0.10
0.6%
72
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
399
+0.11
0.04
167
+0.10
0.04
253
+0.10
0.05
Negative Logits
ingly
-1.76
tered
-1.65
:`
-1.56
github
-1.52
[]{-1.40
)](
-1.39
ificantly
-1.38
cleanup
-1.38
ithub
-1.37
downstream
-1.36
POSITIVE LOGITS
¸
2.59
ī
2.42
Ŀ
2.37
İ
2.29
ij
2.27
Ļª
2.23
ĩ
2.20
»¿
2.14
´
2.11
Ħ
2.09
Activations Density 1.125%