INDEX
Explanations
references to liking a Facebook page
New Auto-Interp
Negative Logits
-0.75
tweeting
-0.65
tweet
-0.64
-0.63
-0.63
tweets
-0.59
tweeted
-0.56
-0.56
-0.56
Tweets
-0.54
POSITIVE LOGITS
resourceCulture
1.00
autorytatywna
0.81
TypedDataSet
0.80
Controllo
0.77
StructEnd
0.73
انيف
0.71
oa̍t
0.70
Roskov
0.69
gynhyrchwyd
0.68
InputBorder
0.68
Activations Density 0.024%