INDEX

Explanations

brand names 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

its

-1.39

razine

-1.24

to

-1.23

 брюки

-1.21

({

-1.21

⸰

-1.20

criminate

-1.17

 grito

-1.13

 ウール

-1.13

 Wreck

-1.13

POSITIVE LOGITS

 наших

1.25

 после

1.23

ERTE

1.20

our

1.19

鈕

1.16

𝐊

1.13

 nuestro

1.12

 więks

1.11

 principales

1.09

 tantos

1.09

Activations Density 0.016%