INDEX

Explanations

code structures and data types

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

wieś

-1.18

 title

-1.11

if

-1.04

 pères

-1.02

 jambes

-1.01

ziesz

-1.01

 fach

-1.00

 highlighted

-0.98

 oper

-0.98

 их

-0.98

POSITIVE LOGITS

 from

1.28

 baterie

1.24

Chakra

1.23

ἃ

1.22

Gambas

1.14

鸸

1.13

 aktivi

1.12

ראי

1.12

 头像

1.11

Besos

1.11

Activations Density 0.029%