INDEX
Explanations
legal clauses and terms related to financial documents
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.10
0.4%
411
+0.08
0.4%
1047
+0.07
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
411
+0.10
0.03
1149
+0.08
0.03
461
+0.07
0.03
Negative Logits
<bos>
-1.30
public
-0.84
,
-0.82
.
-0.81
-0.79
in
-0.79
on
-0.76
-0.76
-0.75
and
-0.74
POSITIVE LOGITS
affor
2.38
stockholm
2.33
lidl
2.32
maneu
2.32
embodi
2.15
eiffel
2.12
scrat
2.11
volunte
2.11
shenan
2.11
michelin
2.10
Activations Density 0.105%