INDEX
Explanations
references to the passage of time, particularly in years and days
New Auto-Interp
Negative Logits
's
-0.19
’s
-0.17
oin
-0.16
ÂŃs
-0.15
anda
-0.15
frey
-0.15
802
-0.15
td
-0.15
ein
-0.15
�s
-0.15
POSITIVE LOGITS
ago
0.22
cape
0.22
’
0.21
'
0.20
/month
0.18
Ago
0.17
PACE
0.17
presso
0.16
ìĶ©
0.16
dozen
0.16
Activations Density 0.056%