INDEX
Explanations
email addresses and dates and times in a specific format
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1343
+0.17
0.5%
24
+0.11
0.3%
1156
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.17
0.06
24
+0.11
0.05
1294
+0.10
0.04
Negative Logits
Fußball
-0.56
معرفی
-0.55
Bereits
-0.55
GEBURTSDATUM
-0.55
Diwedd
-0.54
XmlAccessType
-0.54
Nichts
-0.54
principalColumn
-0.54
AndEndTag
-0.53
ftagPool
-0.53
POSITIVE LOGITS
uhr
0.98
napoli
0.97
ananas
0.94
cæ
0.94
siena
0.94
vns
0.94
cristina
0.94
vne
0.94
hej
0.93
milano
0.93
Activations Density 0.152%