INDEX

Explanations

citations in parentheses

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

∅

-1.46

˂

-1.35

})}

-1.27

 perju

-1.27

няет

-1.26

SPATH

-1.26

----+

-1.23

ImageView

-1.22

𝑛

-1.22

 registre

-1.21

POSITIVE LOGITS

 Hinsicht

1.52

letín

1.20

sandalias

1.20

kitab

1.20

补贴

1.19

 Когда

1.18

 verschill

1.18

ときに

1.16

 ร์

1.16

 bequem

1.16

Activations Density 0.013%