INDEX
Explanations
dates and related numerical expressions
New Auto-Interp
Negative Logits
cool
-0.23
Cool
-0.21
cold
-0.18
cooling
-0.18
cooler
-0.17
Cool
-0.17
cool
-0.16
Cooler
-0.16
979
-0.15
chilly
-0.15
POSITIVE LOGITS
ilit
0.15
aley
0.14
nip
0.14
erap
0.14
EIF
0.14
strand
0.14
bana
0.14
å·¥
0.14
dl
0.14
eut
0.13
Activations Density 0.024%