INDEX
Explanations
news and official statements
New Auto-Interp
Negative Logits
possiamo
0.38
เรา
0.37
我们
0.36
हम
0.35
คุณ
0.35
我们
0.35
мы
0.35
మనం
0.34
synapses
0.34
你们
0.34
POSITIVE LOGITS
spokeswoman
0.40
news
0.39
prnewswire
0.36
spokesman
0.35
cześ
0.34
Gazette
0.34
지난해
0.34
previously
0.33
respond
0.33
emailed
0.33
Activations Density 0.056%