INDEX
Explanations
statistical and mathematical terms or principles
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1253
+0.10
0.3%
129
+0.10
0.3%
71
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
71
+0.10
0.03
129
+0.10
0.02
1653
+0.09
0.03
Negative Logits
fte
-0.84
lts
-0.81
oun
-0.80
··
-0.80
fto
-0.77
lii
-0.76
fter
-0.76
fta
-0.74
mme
-0.74
aen
-0.72
POSITIVE LOGITS
probability
1.09
probabilities
1.03
odds
0.98
probability
0.95
likelihood
0.90
Probability
0.88
chances
0.86
Probability
0.84
chance
0.84
probabilidad
0.83
Activations Density 0.401%