INDEX
Explanations
information related to a news article about teenagers involved in suspicious activities and legal proceedings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1539
+0.09
0.3%
2016
+0.08
0.2%
1601
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
513
+0.09
0.04
1252
+0.08
0.05
1504
+0.08
0.05
Negative Logits
asfal
-0.59
silikon
-0.56
morfo
-0.55
netto
-0.54
stoff
-0.54
balon
-0.54
Modèle
-0.52
rada
-0.51
tille
-0.51
Grecs
-0.50
POSITIVE LOGITS
themselves
0.80
Their
0.75
Their
0.70
themselves
0.70
their
0.68
their
0.67
THEIR
0.64
thier
0.63
berea
0.57
krish
0.54
Activations Density 0.414%