INDEX

Explanations

past tense verbs followed by descriptors

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

rvats

-1.44

but

-1.30

 noce

-1.23

MODIFY

-1.20

xac

-1.19

艮

-1.18

сник

-1.18

'';

-1.17

σκ

-1.16

 quốc

-1.15

POSITIVE LOGITS

1.51

1.29

分別

1.26

Those

1.25

Probably

1.24

也许

1.22

 kabát

1.20

 veya

1.20

Maybe

1.18

Activations Density 0.051%