INDEX

Explanations

version, photos, survey, link, play, signed, noose

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

or

-1.12

 here

-1.09

 cubiertas

-1.02

 iluminación

-1.02

 virtuales

-1.00

 empieza

-0.98

 acá

-0.98

 suavemente

-0.95

 suivie

-0.94

 respetu

-0.93

POSITIVE LOGITS

for

1.44

 для

1.28

สำหรับ

1.16

 עבור

1.13

并

1.05

jā

1.00

嘴唇

0.97

並

0.96

omentos

0.93

ที่จะ

0.92

Activations Density 0.098%