INDEX
Explanations
references to legal defense roles or positions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
376
+0.14
0.8%
156
+0.12
0.7%
348
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
273
+0.14
0.01
348
+0.12
0.01
222
+0.12
0.01
Negative Logits
ĥ½
-4.81
¿½
-4.46
ĥ
-4.33
·
-4.22
ı
-4.13
ĨĴ
-4.05
Į
-4.05
´
-4.04
ĺ
-4.04
Ł
-4.03
POSITIVE LOGITS
iors
2.20
iei
1.93
ÃŃa
1.89
ÃŃf
1.86
ieux
1.85
ivat
1.82
olver
1.80
watson
1.75
ÃŃo
1.74
elist
1.69
Activations Density 0.017%