INDEX

Explanations

names followed by citations

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

allo

-0.12

Ã¶s

-0.12

ajo

-0.11

 spare

-0.10

ELLOW

-0.10

rzy

-0.09

 toItem

-0.09

.Gen

-0.09

tod

-0.09

rij

-0.09

POSITIVE LOGITS

 Estate

0.07

urn

0.07

 pres

0.06

<|fim_middle|>

0.06

HY

0.06

Hy

0.06

bow

0.06

cock

0.05

sud

0.05

 ï»¿

0.05

Activations Density 0.017%