INDEX
Explanations
Legal citations
This neuron responds to the structured case‐header and publication‐notice metadata (court name, docket numbers, filing dates, “NOT FOR PUBLICATION” notices, etc.).
New Auto-Interp
Negative Logits
°N
-0.06
Those
-0.06
_PARAMS
-0.06
Pfizer
-0.06
Interested
-0.06
Fire
-0.06
rak
-0.06
квітня
-0.06
decorating
-0.06
‘s
-0.06
POSITIVE LOGITS
conforme
0.06
آماده
0.06
close
0.06
všichni
0.06
onec
0.06
roar
0.06
ね
0.06
follow
0.06
denotes
0.06
ushi
0.06
Activations Density 0.001%