INDEX
Explanations
references to the holiday Easter
references to the holiday Easter
New Auto-Interp
Negative Logits
rul
-0.73
urally
-0.73
obsc
-0.69
ACTIONS
-0.65
ographed
-0.63
er
-0.63
eric
-0.62
eval
-0.61
ergic
-0.61
erk
-0.61
POSITIVE LOGITS
Eggs
1.20
Bunny
1.11
Egg
1.00
eggs
0.99
bunny
0.93
brook
0.90
Surprise
0.87
egg
0.86
ween
0.85
lyn
0.84
Activations Density 0.031%