INDEX
Explanations
phrases indicating quantity, specifically the term "couple" in various contexts
New Auto-Interp
Negative Logits
adil
-0.19
ayers
-0.17
roy
-0.17
ers
-0.16
nám
-0.15
jav
-0.15
gebung
-0.15
rug
-0.15
arp
-0.15
s
-0.15
POSITIVE LOGITS
dozen
0.28
XS
0.16
hundred
0.16
eo
0.16
ouser
0.16
mint
0.15
DTV
0.15
ĵ
0.15
-digit
0.15
aus
0.15
Activations Density 0.021%