INDEX
Explanations
emotive expressions, particularly related to personal sentiment and feelings
New Auto-Interp
Negative Logits
^(@)
-1.35
Efq
-1.30
doubtnut
-1.29
Jefus
-1.19
lowa
-1.19
་་
-1.15
-"
-1.13
。"
-1.12
...'
-1.12
photolibrary
-1.10
POSITIVE LOGITS
“
1.78
’
1.76
”
1.74
‘
1.57
“
1.50
.’
1.48
’,
1.46
.”
1.45
’.
1.41
,’
1.40
Activations Density 0.209%