INDEX
Explanations
narratives related to crime and justice
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
764
+0.21
0.7%
946
+0.11
0.3%
604
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
764
+0.21
0.09
100
+0.11
0.07
16
+0.09
0.08
Negative Logits
<bos>
-0.94
ContentAsync
-0.52
terceiros
-0.46
useRouter
-0.44
getIntent
-0.43
IInter
-0.42
parceiros
-0.41
fundamentos
-0.41
vó
-0.41
trouva
-0.41
POSITIVE LOGITS
Bengt
0.74
Bartholo
0.70
Abbé
0.67
Lycée
0.63
Shakspeare
0.63
Rued
0.62
Knud
0.62
pamph
0.60
Ruman
0.60
Penna
0.58
Activations Density 1.139%