INDEX
Explanations
emotional expressions and dialogue in the text
New Auto-Interp
Negative Logits
autorytatywna
-0.59
bootstrapcdn
-0.57
IsMutable
-0.52
snippetHide
-0.51
Wicidata
-0.49
ագրություններ
-0.49
いいですね
-0.48
のですね
-0.48
Saluti
-0.47
LOL
-0.47
POSITIVE LOGITS
Shut
0.47
Shut
0.47
Guys
0.47
shut
0.46
Guys
0.44
idiot
0.42
stupid
0.41
Stupid
0.41
stop
0.41
Promise
0.41
Activations Density 0.100%