INDEX
Explanations
the last names of politicians
names of individuals, particularly political figures
New Auto-Interp
Negative Logits
spring
-0.75
RIS
-0.74
Sleeping
-0.66
Reboot
-0.64
istically
-0.63
actual
-0.62
iour
-0.61
hottest
-0.61
etting
-0.60
ecycle
-0.60
POSITIVE LOGITS
yden
1.16
hof
0.95
boro
0.93
stein
0.87
ovo
0.81
quist
0.80
horn
0.80
arthed
0.77
berg
0.77
baum
0.76
Activations Density 0.006%