INDEX
Explanations
terms related to loans and borrowing in a financial context
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.23
1.3%
421
+0.12
0.7%
1870
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1622
+0.23
0.02
421
+0.12
0.02
1553
+0.10
0.02
Negative Logits
<bos>
-2.69
/***
-0.77
<?
-0.73
/**
-0.60
ⓧ
-0.59
-0.59
contend
-0.55
prioritize
-0.55
didSet
-0.53
distribute
-0.53
POSITIVE LOGITS
loan
1.16
loans
1.14
Loan
1.14
Loans
1.12
Loan
1.08
Loans
1.07
LOAN
1.06
bandung
1.06
loan
1.00
jawa
0.97
Activations Density 0.031%