INDEX
Explanations
words related to financial transactions and monetary values
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
410
+0.18
1.0%
140
+0.14
0.8%
501
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
501
+0.18
0.01
140
+0.14
0.02
410
+0.14
0.02
Negative Logits
ership
-1.87
alities
-1.81
cgi
-1.75
cooker
-1.73
hower
-1.72
amiento
-1.68
ional
-1.65
behalf
-1.64
gence
-1.62
ariat
-1.60
POSITIVE LOGITS
Īĺ
2.62
ĩ
2.54
²
2.42
¥
2.41
ĨĴ
2.39
¶
2.38
Ĥ¬
2.36
ı
2.24
ī
2.21
¸
2.13
Activations Density 0.043%