INDEX

Explanations

models and algorithms

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

ׇ

-1.67

 النبات

-1.47

 tumbuhan

-1.36

 cortar

-1.32

 сахара

-1.29

 byla

-1.27

 supermercados

-1.24

----|

-1.23

 where

-1.23

washer

-1.23

POSITIVE LOGITS

 бампер

1.62

 موبایل

1.27

1.24

 itong

1.21

וּ

1.18

ַּ

1.16

results

1.16

おわりに

1.13

jadi

1.10

 ușor

1.10

Activations Density 0.026%