INDEX

Explanations

describes a state or characteristic

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

abi

-0.12

 recently

-0.12

 originally

-0.11

 initially

-0.11

 yesterday

-0.10

 last

-0.10

 unsuccessfully

-0.10

 lately

-0.09

 earlier

-0.09

 Yesterday

-0.09

POSITIVE LOGITS

now

0.19

now

0.15

 currently

0.13

/w

0.13

(ed

0.13

NOW

0.13

Was

0.12

zed

0.12

äºĨ

0.11

was

0.11

Activations Density 1.672%