INDEX

Explanations

Andrew, Ireland, argin

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ellem

-0.09

hta

-0.08

ledon

-0.08

tot

-0.07

ä¸įè¯¦

-0.07

}s

-0.07

æĿ¥ä¹ĭ

-0.07

macher

-0.07

á»Ŀ

-0.07

ä½Ĩæĺ¯æĪĳ

-0.07

POSITIVE LOGITS

—the

0.17

 à¸ĭà¸¶à¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ

0.12

à¸ĭà¸¶à¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ

0.12

 selaku

0.11

ä½ľä¸º

0.10

—which

0.09

—an

0.09

(the

0.09

—a

0.09

ä¹Łå°±æĺ¯

0.08

Activations Density 0.447%