INDEX

Explanations

The neuron fires on words and phrases expressing legal or constitutional “rights” or protections (e.g. right to free speech, right to choose).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

د

0.98

ع

0.95

IDs

0.86

URLs

0.82

 повы

0.81

árm

0.80

ώντας

0.80

ى

0.79

ATE

0.79

MPs

0.78

POSITIVE LOGITS

 rights

1.48

 freedoms

1.41

 freedom

1.36

 Rights

1.35

 RIGHTS

1.23

 diritti

1.20

 liberty

1.17

 droits

1.13

rights

1.13

 libertà

1.13

Activations Density 0.076%