INDEX
Explanations
references to legal terms and actions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
23
+0.30
1.7%
365
+0.13
0.7%
333
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
23
+0.30
0.08
56
+0.13
0.11
450
+0.12
0.09
Negative Logits
»
-2.53
¼
-2.20
»¿
-2.14
Ħ
-2.13
½
-2.03
¢
-2.00
¥
-1.99
Ľ
-1.97
į
-1.96
ı
-1.96
POSITIVE LOGITS
kinase
1.57
*\
1.50
Copyright
1.45
enu
1.40
amil
1.40
^{1.40
**
1.37
hib
1.35
hip
1.34
^[@
1.33
Activations Density 1.515%