INDEX
Explanations
names that end with "ner"
the term "ner," indicating a focus on entities or individuals associated with that suffix
New Auto-Interp
Negative Logits
ĸļ
-0.69
urities
-0.66
avorite
-0.65
EMP
-0.64
oral
-0.63
Occupations
-0.63
UTC
-0.63
runaway
-0.61
VIDE
-0.58
UV
-0.58
POSITIVE LOGITS
getic
1.05
ding
1.01
gie
0.93
ger
0.88
ning
0.86
idge
0.86
stein
0.85
nen
0.85
lund
0.84
sonian
0.84
Activations Density 0.024%