INDEX
Explanations
mentions of time (past or specific time)
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.32
1.2%
184
+0.27
1.0%
1967
+0.16
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
184
+0.32
0.01
648
+0.27
0.01
1842
+0.16
0.02
Negative Logits
embodi
-0.68
encomp
-0.63
cytoplas
-0.63
impra
-0.62
unfore
-0.61
indestru
-0.60
GEBURTSDATUM
-0.59
Moslem
-0.58
viciss
-0.58
Ecclesiastical
-0.58
POSITIVE LOGITS
<bos>
0.66
gela
0.53
prends
0.50
Junho
0.50
zove
0.50
PLWABN
0.50
comprends
0.50
gradova
0.50
Allociné
0.49
pourrais
0.49
Activations Density 0.070%