INDEX
Explanations
programming language elements and code snippets
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1224
+0.12
0.4%
845
+0.10
0.3%
1177
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1343
+0.12
0.06
1429
+0.10
0.04
382
+0.10
0.04
Negative Logits
milf
-1.29
fta
-1.24
hentai
-1.23
guarante
-1.21
snoopy
-1.20
fte
-1.19
purcha
-1.16
embra
-1.14
suspic
-1.13
fto
-1.13
POSITIVE LOGITS
TagMode
0.65
Datuak
0.63
kasarigan
0.58
EndGlobalSection
0.58
Autoritní
0.55
IVEREF
0.55
SharedDtor
0.53
<>",
0.53
betweenstory
0.52
ViewFeatures
0.52
Activations Density 0.332%