INDEX
Explanations
phrases related to arguments or discussions
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1978
+0.12
0.3%
194
+0.09
0.3%
453
+0.09
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
468
+0.12
0.03
981
+0.09
0.04
1826
+0.09
0.00
Negative Logits
Simult
-0.81
indestru
-0.76
depic
-0.74
pym
-0.74
Rued
-0.74
renfer
-0.73
maneu
-0.71
luigi
-0.69
circums
-0.69
plebe
-0.69
POSITIVE LOGITS
商品説明
0.68
SDLK
0.53
NOPQRST
0.53
SerializedSize
0.53
InputDecoration
0.52
istemas
0.51
"?
0.50
miele
0.50
KURZBESCHREIBUNG
0.49
ohist
0.49
Activations Density 0.315%