INDEX
Explanations
references to a specific person's name, particularly "Adam"
New Auto-Interp
Negative Logits
--
-0.74
+#+#
-0.71
--
-0.70
-0.65
afficheront
-0.62
енча
-0.58
enggak
-0.56
Normdatei
-0.56
-0.55
)--
-0.53
POSITIVE LOGITS
„
1.69
„
1.66
(„
1.48
„,
1.09
‚
1.00
?“
0.80
“,
0.76
,,
0.72
exitRule
0.71
ViewHolder
0.71
Activations Density 0.065%