INDEX
Explanations
labels or identifiers related to source files
New Auto-Interp
Negative Logits
Monfieur
-0.77
Efq
-0.74
itſelf
-0.68
myſelf
-0.65
reafon
-0.64
himſelf
-0.63
themſelves
-0.62
XmlEnum
-0.62
RSSSF
-0.61
Majefty
-0.61
POSITIVE LOGITS
Source
0.78
FetchType
0.71
Edward
0.64
Билгалдахарш
0.58
Revenir
0.57
NP
0.57
Edward
0.56
ymce
0.55
Storage
0.53
clientX
0.53
Activations Density 0.109%