INDEX

Explanations

judges and court titles

The neuron detects mentions of courts, judges, magistrates, appeals panels, and other legal‐judicial titles and names.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-1.22

-1.06

-1.03

-1.02

 blumen

-1.01

our

-1.01

its

-1.00

-0.99

 μας

-0.98

POSITIVE LOGITS

结语

1.28

animales

1.23

sprü

1.23

المل

1.21

 urat

1.18

tentu

1.17

 производстве

1.17

ַּ

1.15

zurück

1.15

getting

1.14

Activations Density 0.136%