INDEX
Explanations
terms related to dining and dining experiences
New Auto-Interp
Negative Logits
Fitzgerald
-0.64
gerald
-0.62
simum
-0.59
IAH
-0.56
führt
-0.56
lış
-0.56
baratos
-0.55
macht
-0.55
stt
-0.55
atchewan
-0.54
POSITIVE LOGITS
dining
2.83
Dining
2.58
Dining
2.48
dining
2.46
dine
1.84
dined
1.79
Dine
1.46
diners
1.44
Dine
1.42
DIN
1.40
Activations Density 0.077%