INDEX
Explanations
names or variations of the name "Lob."
New Auto-Interp
Negative Logits
iard
-0.18
ifter
-0.16
oust
-0.16
ived
-0.16
uese
-0.15
ummy
-0.15
azer
-0.15
ptime
-0.15
vore
-0.15
undry
-0.15
POSITIVE LOGITS
bing
0.20
fusc
0.20
ility
0.19
late
0.18
ber
0.18
ī
0.18
berman
0.17
noxious
0.17
bed
0.17
pena
0.16
Activations Density 0.038%