INDEX
Explanations
questions that start with "Did" and inquire about someone's experiences or actions
New Auto-Interp
Negative Logits
antMatchers
-1.17
SharedDtor
-0.97
HomeAsUpEnabled
-0.95
كومونز
-0.90
trx
-0.89
Rhonda
-0.88
いる
-0.88
sella
-0.87
Sambo
-0.86
stateMutability
-0.86
POSITIVE LOGITS
did
1.12
DID
1.12
did
1.10
Did
1.05
DID
0.92
Did
0.89
Didi
0.85
came
0.84
had
0.83
Went
0.83
Activations Density 0.128%