INDEX
Explanations
phrases related to residential areas or activities
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1178
+0.14
0.7%
1323
+0.13
0.7%
369
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
990
+0.14
0.03
369
+0.13
0.03
1178
+0.13
0.03
Negative Logits
<bos>
-1.73
AutoScale
-0.60
MarshalTo
-0.58
Κα
-0.58
ProtoMessage
-0.58
Даль
-0.58
hintText
-0.58
devise
-0.56
o
-0.55
englanniksi
-0.55
POSITIVE LOGITS
depic
1.37
unden
1.35
disagre
1.35
Residential
1.34
ftu
1.32
fuf
1.30
maneu
1.29
Residential
1.27
fta
1.27
wien
1.26
Activations Density 0.287%