INDEX
Explanations
occurrences of the word "Mun."
New Auto-Interp
Negative Logits
.fm
-0.18
adows
-0.15
adc
-0.15
lant
-0.15
ieber
-0.14
adors
-0.14
GS
-0.14
webtoken
-0.14
weather
-0.13
isle
-0.13
POSITIVE LOGITS
itions
0.28
roe
0.26
ificent
0.25
ster
0.24
ition
0.22
oz
0.22
nelly
0.21
STER
0.20
incipal
0.19
shi
0.19
Activations Density 0.004%