INDEX
Explanations
references to being on board or aboard a vehicle or vessel
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
421
+0.16
0.5%
1983
+0.12
0.4%
1052
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
421
+0.16
0.02
1983
+0.12
0.02
1052
+0.12
0.02
Negative Logits
PostExecute
-0.50
("")]
-0.49
ext
-0.48
WebControls
-0.47
leche
-0.47
ViewFeatures
-0.47
ligence
-0.46
RequestMethod
-0.46
펴
-0.45
literals
-0.45
POSITIVE LOGITS
shenan
1.24
hentai
1.18
hairc
1.15
milf
1.11
depic
1.08
McLaugh
1.08
disreg
1.07
indestru
1.07
reluct
1.05
waifu
1.04
Activations Density 0.068%