INDEX
Explanations
phrases related to legal proceedings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1741
+0.21
0.7%
50
+0.20
0.7%
2019
+0.15
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
16
+0.21
0.06
50
+0.20
0.04
1435
+0.15
0.05
Negative Logits
bâton
-0.89
puits
-0.86
[''
-0.81
couteau
-0.80
trouva
-0.80
'&#
-0.78
loup
-0.78
doigt
-0.77
noël
-0.77
rempliss
-0.77
POSITIVE LOGITS
entire
0.66
Katso
0.61
reason
0.61
same
0.58
Mitä
0.56
Demikian
0.55
goal
0.54
biggest
0.54
الحياه
0.54
onus
0.53
Activations Density 0.227%