INDEX
Explanations
mentions of financial institutions, particularly banks
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
197
+0.15
0.6%
1562
+0.15
0.6%
1376
+0.15
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1562
+0.15
0.04
1376
+0.15
0.04
197
+0.15
0.04
Negative Logits
daz
-0.65
vern
-0.65
overla
-0.64
dora
-0.64
purcha
-0.62
guarante
-0.62
alre
-0.62
zimmer
-0.61
ofre
-0.60
noel
-0.60
POSITIVE LOGITS
bank
1.49
bank
1.37
Bank
1.33
banks
1.31
Bank
1.26
BANK
1.20
banking
1.16
Banks
1.16
BANK
1.16
banks
1.15
Activations Density 0.074%