INDEX
Explanations
descriptions of rooms or accommodations in residential or commercial properties
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.18
1.0%
1604
+0.11
0.6%
597
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1634
+0.18
0.03
1013
+0.11
0.03
166
+0.10
0.02
Negative Logits
<bos>
-2.88
Geplaatst
-0.77
IVEREF
-0.73
ProtoMessage
-0.71
addCriterion
-0.70
mergeFrom
-0.68
JspWriter
-0.67
uxxxx
-0.66
introduce
-0.65
HasForeignKey
-0.64
POSITIVE LOGITS
affor
1.65
increa
1.51
scrat
1.50
hairc
1.48
inev
1.48
milf
1.48
maneu
1.46
impra
1.46
fortn
1.45
wikihow
1.45
Activations Density 0.130%