INDEX

Explanations

according to + organization

The neuron flags occurrences of formal source or citation labels (like “Survey,” “Commission,” “Agency,” “Report,” “Blog,” etc.) that identify data sources or official publications.

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

our

-1.55

of

-1.21

we

-1.19

-1.13

my

-1.13

the

-1.10

to

-1.07

·

-1.00

-0.99

POSITIVE LOGITS

 yesterday

1.30

 cuire

1.28

álbum

1.13

potensi

1.10

ῆ

1.09

řád

1.09

 finas

1.08

 navigu

1.08

Перевод

1.07

película

1.05

Activations Density 0.035%