INDEX
Explanations
phrases related to proximity or closeness
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.11
0.4%
1035
+0.10
0.3%
1993
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1244
+0.11
0.03
1081
+0.10
0.04
1035
+0.09
0.04
Negative Logits
IDATE
-0.44
lojik
-0.44
IsNotNull
-0.41
part
-0.40
veroor
-0.40
ี่ยม
-0.39
Paglinawan
-0.39
role
-0.39
WEB
-0.39
cupa
-0.38
POSITIVE LOGITS
autunno
0.95
archivio
0.93
umbro
0.90
affez
0.85
milano
0.85
hcm
0.84
palio
0.84
lapto
0.83
nomine
0.82
meis
0.82
Activations Density 0.137%