INDEX
Explanations
technical terms related to specific software frameworks and programming languages
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.44
2.0%
1577
+0.31
1.4%
1967
+0.21
1.0%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1967
+0.44
0.13
453
+0.31
0.19
599
+0.21
0.20
Negative Logits
„,
-1.10
thut
-1.10
maneu
-1.00
meis
-0.99
withal
-0.99
riviera
-0.98
Shakspeare
-0.98
abnorm
-0.97
Czechos
-0.97
madonna
-0.97
POSITIVE LOGITS
<bos>
1.13
/***
0.57
also
0.47
0.46
ⓧ
0.43
انجليز
0.42
other
0.41
other
0.41
座
0.41
lateinit
0.40
Activations Density 12.563%