INDEX
Explanations
words related to software and technology performance
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
50
+0.17
0.5%
1150
+0.15
0.5%
1741
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
332
+0.17
0.06
16
+0.15
0.06
50
+0.12
0.05
Negative Logits
indeb
-0.91
pecuni
-0.86
affari
-0.83
abbra
-0.83
kompati
-0.76
erk
-0.76
lende
-0.76
seduta
-0.74
socie
-0.74
soste
-0.73
POSITIVE LOGITS
own
0.68
latest
0.66
s
0.64
masterful
0.61
penchant
0.60
infamous
0.59
insatiable
0.59
insistence
0.57
inaugural
0.56
s
0.55
Activations Density 0.275%