INDEX
Explanations
phrases related to financial support decisions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1937
+0.13
0.5%
370
+0.12
0.4%
78
+0.11
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
370
+0.13
0.03
1937
+0.12
0.03
765
+0.11
0.03
Negative Logits
Verg
-0.44
Simultaneously
-0.41
Koning
-0.41
Really
-0.40
митри
-0.40
Schäfer
-0.39
Rekord
-0.39
subsidi
-0.38
cm
-0.38
Kand
-0.38
POSITIVE LOGITS
DUE
1.00
due
0.89
Due
0.85
due
0.81
Due
0.80
DUE
0.73
dégust
0.70
nephe
0.69
comuna
0.69
Debido
0.68
Activations Density 0.066%