INDEX
Explanations
comparative phrases and expressions of expectation or belief
New Auto-Interp
Negative Logits
shouldn
-0.18
weren
-0.16
ä¸įä¼ļ
-0.15
меÑĤÑĮ
-0.15
ulur
-0.15
Didn
-0.15
hasn
-0.14
決
-0.14
haven
-0.14
doesn
-0.14
POSITIVE LOGITS
barg
0.29
bargain
0.23
Barg
0.22
bargaining
0.22
realize
0.22
realized
0.21
realise
0.21
realised
0.20
realizes
0.19
perhaps
0.19
Activations Density 0.054%