INDEX
Explanations
explanations and descriptions related to technical concepts and inventions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.15
0.4%
872
+0.11
0.3%
46
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1801
+0.15
0.03
46
+0.11
0.04
62
+0.08
0.04
Negative Logits
keramik
-0.71
kooper
-0.71
kasa
-0.71
kte
-0.69
kosme
-0.68
<^
-0.67
„,
-0.67
elek
-0.66
maksi
-0.66
fré
-0.66
POSITIVE LOGITS
<bos>
0.69
considering
0.63
compared
0.60
retrospect
0.59
hindsight
0.58
considering
0.57
viewed
0.53
zumal
0.53
">/
0.51
vestiti
0.51
Activations Density 0.343%