INDEX
Explanations
personal experiences and feelings
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.23
1.1%
1978
+0.15
0.7%
78
+0.12
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
78
+0.23
0.08
1415
+0.15
0.05
805
+0.12
0.06
Negative Logits
<bos>
-3.20
<?
-0.82
/**
-0.81
/*++
-0.76
ⓧ
-0.74
-0.67
żdy
-0.61
InitStruct
-0.60
SourceChecksum
-0.60
,
-0.58
POSITIVE LOGITS
bandung
1.42
Minang
1.23
valencia
1.21
jawa
1.19
affor
1.18
roberto
1.16
milano
1.16
!!</
1.15
stockholm
1.14
leonardo
1.14
Activations Density 0.820%