INDEX
Explanations
the word "duck" appearing in the text
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1328
+0.23
1.2%
68
+0.19
1.0%
101
+0.15
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1328
+0.23
0.06
690
+0.19
0.04
1741
+0.15
0.00
Negative Logits
Vegeu
-0.79
<bos>
-0.72
Архівовано
-0.69
EndContext
-0.67
RectangleBorder
-0.66
ParallelGroup
-0.65
("")]
-0.63
الرياضيه
-0.61
+#+
-0.60
FontOfSize
-0.60
POSITIVE LOGITS
unspeak
1.12
maneu
1.06
reluct
1.05
Duck
1.03
apprehen
1.02
Duck
1.01
pamph
1.00
philanth
1.00
duck
0.99
gaily
0.98
Activations Density 0.497%