INDEX
Explanations
instances of punctuation and pauses in speech
New Auto-Interp
Negative Logits
ippi
-0.16
mai
-0.16
riel
-0.15
agoon
-0.15
acob
-0.15
chter
-0.14
ipt
-0.14
izm
-0.14
elli
-0.13
abei
-0.13
POSITIVE LOGITS
776
0.15
κÏħ
0.15
ceptar
0.14
ivar
0.14
ivid
0.14
pub
0.13
Ros
0.13
entr
0.13
tire
0.13
itÃł
0.13
Activations Density 0.279%