INDEX
Explanations
legal terms and court proceedings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
382
+0.10
0.3%
453
+0.10
0.3%
1150
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1629
+0.10
0.03
499
+0.10
0.04
1014
+0.09
0.04
Negative Logits
thermomix
-1.09
fluo
-1.07
nutella
-1.03
gmbh
-1.00
tricot
-1.00
meis
-0.96
wien
-0.95
bonbons
-0.95
bordeaux
-0.90
embodi
-0.90
POSITIVE LOGITS
sentenced
0.61
zegor
0.56
Sentence
0.54
ImageContext
0.53
Demografía
0.53
addPreferredGap
0.53
amaño
0.51
Prosecutors
0.50
sentence
0.50
careous
0.50
Activations Density 0.297%