INDEX
Explanations
the beginning or end of the text
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.44
5.7%
1741
+0.07
0.8%
1870
+0.04
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
15
+0.44
0.32
800
+0.07
0.33
354
+0.04
0.32
Negative Logits
unspeak
-2.77
reluct
-2.62
disgra
-2.56
unlaw
-2.56
shenan
-2.46
impractica
-2.44
impra
-2.41
ineffec
-2.39
horrend
-2.38
disagre
-2.37
POSITIVE LOGITS
<bos>
14.47
GEBURTSDATUM
2.54
expandindo
2.52
betweenstory
2.49
Autoritní
2.46
تقاوى
2.20
Italijani
2.17
Administrativna
2.16
Paglinawan
2.12
kasarigan
2.11
Activations Density 0.088%