INDEX
Explanations
numeric and statistical information related to measurements or scores
New Auto-Interp
Negative Logits
SuppressMessage
-0.60
CopyWith
-0.57
Geplaatst
-0.53
--
-0.52
sa
-0.51
ut
-0.51
“
-0.50
rippa
-0.49
AsUp
-0.49
"
-0.49
POSITIVE LOGITS
GIPHY
0.86
itſelf
0.83
varandra
0.81
myſelf
0.77
ſche
0.73
purpoſe
0.73
ſelves
0.72
Chriftian
0.72
первых
0.72
houſe
0.70
Activations Density 0.097%