INDEX
Explanations
The neuron detects occurrences of the legal phrase “statute of limitations.”
New Auto-Interp
Negative Logits
elbows
-0.08
cleaners
-0.07
Bern
-0.07
“[
-0.06
ileri
-0.06
_beam
-0.06
win
-0.06
Bihar
-0.06
-control
-0.06
Mix
-0.06
POSITIVE LOGITS
statutory
0.09
statute
0.08
statutes
0.08
0.08
[str
0.08
scripture
0.07
ST
0.07
ster
0.07
Stra
0.07
word
0.07
Activations Density 0.003%