INDEX
Explanations
references to individuals' testimonies and interactions related to legal cases
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
480
+0.14
0.8%
119
+0.13
0.7%
497
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
497
+0.14
-0.02
261
+0.13
-0.01
119
+0.12
0.06
Negative Logits
ridges
-1.60
ylum
-1.58
injury
-1.56
ités
-1.47
ifications
-1.46
jection
-1.43
asers
-1.42
asic
-1.41
urns
-1.40
asms
-1.39
POSITIVE LOGITS
fe
1.68
ļ
1.56
sympath
1.52
°
1.47
agm
1.44
¾
1.42
Feb
1.41
º
1.40
©
1.39
parte
1.35
Activations Density 3.690%