INDEX
Explanations
dates and events mentioned in the text
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.33
1.7%
2019
+0.15
0.8%
814
+0.08
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2019
+0.33
0.28
1699
+0.15
0.21
381
+0.08
0.11
Negative Logits
<bos>
-2.44
ⓧ
-1.30
/**
-1.12
quitted
-1.12
<?
-1.10
intersper
-1.09
-1.02
/***
-1.02
frastructure
-0.88
forbear
-0.85
POSITIVE LOGITS
ieb
0.62
Karakter
0.59
Presenta
0.54
marea
0.52
Cerca
0.49
confec
0.48
mercad
0.48
Same
0.47
seksi
0.47
Rng
0.47
Activations Density 2.848%