INDEX
Explanations
phrases related to public figures or leadership positions
New Auto-Interp
Negative Logits
-0.75
-0.51
SharedDtor
-0.42
padx
-0.41
/*++
-0.38
//
-0.37
MergeFrom
-0.36
jspb
-0.36
typelib
-0.36
/*
-0.35
POSITIVE LOGITS
Scottish
1.52
Scotland
1.41
Scottish
1.38
Scotland
1.30
Glasgow
1.28
Scots
1.24
scottish
1.23
Edinburgh
1.18
Glasgow
1.17
Scotsman
1.10
Activations Density 0.349%