INDEX
Explanations
mentions of law enforcement activities and investigations
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
946
+0.14
0.4%
658
+0.12
0.3%
1499
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
658
+0.14
0.08
1048
+0.12
0.04
946
+0.10
0.06
Negative Logits
dirait
-0.82
trouva
-0.81
peppa
-0.78
tupperware
-0.77
ecru
-0.77
gouver
-0.76
gabri
-0.74
hairc
-0.74
giorgio
-0.72
cristina
-0.72
POSITIVE LOGITS
Vaata
0.59
("="0.57
Referencoj
0.56
patrolling
0.55
investigating
0.54
Sqft
0.54
escort
0.52
patrol
0.52
Solución
0.51
Kaip
0.51
Activations Density 0.469%