INDEX
Explanations
references to the name "Thomas."
New Auto-Interp
Negative Logits
legungen
-0.70
#
-0.69
Verdana
-0.69
Af
-0.69
jegy
-0.67
Scrip
-0.67
IconButton
-0.65
Abitanti
-0.63
sfx
-0.62
Arend
-0.62
POSITIVE LOGITS
Thomas
1.52
Thomas
1.41
THOMAS
1.38
Tom
1.35
thomas
1.33
THOMAS
1.33
Tom
1.32
thomas
1.18
TOM
1.11
Tommaso
1.08
Activations Density 0.052%