INDEX
Explanations
occurrences of the name "Tony."
New Auto-Interp
Negative Logits
zeÅĦ
-0.18
sWith
-0.17
ież
-0.16
alach
-0.16
pas
-0.16
rend
-0.15
nÃło
-0.15
rying
-0.15
bote
-0.15
bage
-0.14
POSITIVE LOGITS
ingo
0.15
iface
0.15
onto
0.14
keit
0.14
embre
0.14
ivia
0.14
вано
0.14
wards
0.14
Stern
0.14
undan
0.14
Activations Density 0.012%