INDEX
Explanations
references to dancing
occurrences of the word "dancing" and its variations in various contexts
New Auto-Interp
Negative Logits
PF
-0.73
atch
-0.68
omo
-0.67
POR
-0.67
çīĪ
-0.65
GV
-0.63
rompt
-0.62
krit
-0.62
artment
-0.61
orio
-0.60
POSITIVE LOGITS
dancing
1.07
danced
0.97
Dancing
0.96
dances
0.85
dancers
0.81
wagon
0.80
goers
0.79
tails
0.79
weed
0.79
tail
0.78
Activations Density 0.011%