INDEX
Explanations
quotes and reported speech
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1252
+0.12
0.3%
946
+0.11
0.3%
194
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
946
+0.12
0.06
1252
+0.11
0.05
1551
+0.10
0.04
Negative Logits
namorados
-0.68
parlano
-0.66
readObject
-0.65
meninos
-0.61
parlar
-0.61
HasAnnotation
-0.60
Paglinawan
-0.60
rinfo
-0.60
casais
-0.59
Sucesor
-0.59
POSITIVE LOGITS
McLaugh
1.03
reluct
0.85
apprehen
0.84
members
0.83
Shakspeare
0.83
Bartholo
0.82
Vaugh
0.81
Juf
0.81
groupName
0.81
group
0.80
Activations Density 0.760%