INDEX
Explanations
phrases related to sports and scoring situations
New Auto-Interp
Negative Logits
ambre
-0.17
ksi
-0.16
omer
-0.15
pornografia
-0.14
PTION
-0.14
lob
-0.14
/ic
-0.14
ghi
-0.13
æ°¸ä¹ħ
-0.13
sov
-0.13
POSITIVE LOGITS
oler
0.15
jee
0.15
ben
0.14
yro
0.14
_phys
0.14
_adv
0.14
foot
0.14
γον
0.13
RefCount
0.13
Wendy
0.13
Activations Density 0.003%