INDEX
Explanations
mentions of the name "Nathan."
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1404
+0.22
1.3%
251
+0.14
0.8%
1921
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
227
+0.22
0.03
1741
+0.14
0.00
1343
+0.14
0.03
Negative Logits
<bos>
-0.96
HideFlags
-0.70
Hélène
-0.57
Аб
-0.56
Су
-0.56
λ
-0.55
FlatStyle
-0.54
Kích
-0.54
Су
-0.53
resizeMode
-0.52
POSITIVE LOGITS
Nathan
1.42
Nathan
1.38
casio
1.28
fta
1.26
wien
1.23
squa
1.17
milf
1.14
scrat
1.14
:,,
1.13
vhs
1.13
Activations Density 0.202%