INDEX

Explanations

Technical documentation

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

spir

-0.28

uncate

-0.27

 launched

-0.26

ered

-0.25

å¢¨

-0.25

 leading

-0.25

oute

-0.24

æĶ¶èİ·

-0.24

é¢Ĩ

-0.24

 Ð¿Ð¾Ð»Ñı

-0.24

POSITIVE LOGITS

ension

0.29

éĿ©åĳ½

0.28

 Hoover

0.26

inq

0.26

.sun

0.25

 revolution

0.25

 Revolution

0.25

pNext

0.24

 JsonRequest

0.24

å¼ĢæĶ¾å¼ı

0.24

Activations Density 0.878%