INDEX
Explanations
phrases related to a person named "Fran"
the name "Fran"
New Auto-Interp
Negative Logits
eenth
-0.81
accompanied
-0.73
holders
-0.72
een
-0.69
gow
-0.69
tomat
-0.69
scape
-0.68
arov
-0.67
orld
-0.66
omething
-0.66
POSITIVE LOGITS
Dres
1.05
furt
0.97
zen
0.92
Fran
0.91
ç
0.90
ois
0.87
cium
0.84
ci
0.83
kel
0.83
thal
0.82
Activations Density 0.021%