INDEX

Explanations

Code/Technical documentation

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portail

-0.88

PreferredItem

-0.80

InjectAttribute

-0.71

الحياه

-0.71

#+#

-0.69

Vidite

-0.66

 تانيه

-0.64

脚注の使い方

-0.63

Спасылкі

-0.62

 мәкал

-0.61

POSITIVE LOGITS

omas

0.51

uel

0.48

Flop

0.47

onias

0.44

 Digest

0.43

Bonsoir

0.43

ilan

0.42

SIZ

0.42

 Dulles

0.41

 tabindex

0.41

Activations Density 0.047%