INDEX
Explanations
contact information and technical details
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
381
+0.18
0.6%
82
+0.11
0.4%
776
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
82
+0.18
0.07
25
+0.11
0.07
1565
+0.10
0.06
Negative Logits
ananas
-1.43
venuto
-1.41
franz
-1.35
meis
-1.35
susun
-1.34
nuoc
-1.33
dises
-1.33
territo
-1.32
Võ
-1.32
canel
-1.31
POSITIVE LOGITS
It
0.85
It
0.83
wasn
0.82
consists
0.81
'
0.81
is
0.80
doesn
0.79
was
0.78
seems
0.78
’
0.77
Activations Density 0.285%