INDEX
Explanations
mentions of housing and related terms
New Auto-Interp
Negative Logits
thal
-0.18
isk
-0.16
adin
-0.16
ewe
-0.15
isch
-0.14
zym
-0.14
resentation
-0.14
ever
-0.14
chia
-0.14
hitch
-0.14
POSITIVE LOGITS
orny
0.19
oret
0.17
/home
0.16
/feed
0.16
/Home
0.15
guest
0.15
boats
0.15
clean
0.15
mates
0.15
frau
0.15
Activations Density 0.014%