INDEX
Explanations
expressions of concern or interest in social issues and community engagement
New Auto-Interp
Negative Logits
currently
-0.18
currently
-0.16
tonight
-0.16
aremos
-0.15
tomorrow
-0.15
缮åīį
-0.15
agens
-0.15
ngen
-0.15
LENG
-0.14
ÙĤÙĪÙĦ
-0.14
POSITIVE LOGITS
was
0.25
was
0.24
wasn
0.24
Was
0.21
ÙĪÙĥاÙĨ
0.21
estaba
0.20
seemed
0.20
ëĭ¹ìĭľ
0.20
habÃŃa
0.20
hadn
0.20
Activations Density 0.656%