INDEX
Explanations
phrases related to speculation or theories
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1506
+0.11
0.4%
1363
+0.11
0.4%
1133
+0.11
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1372
+0.11
0.03
411
+0.11
0.03
1363
+0.11
0.03
Negative Logits
shutterstock
-0.60
/*!
-0.58
solidar
-0.56
Caratter
-0.52
apparti
-0.52
realme
-0.51
impon
-0.50
reputa
-0.50
netto
-0.47
MSN
-0.47
POSITIVE LOGITS
speculating
1.01
speculate
0.97
speculation
0.89
speculated
0.84
speculations
0.83
jecture
0.79
xPos
0.76
jectures
0.75
userType
0.72
conjecture
0.70
Activations Density 0.106%