INDEX

Explanations

Technical language

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

apt

-0.28

 Polit

-0.28

åľľ

-0.25

ä»ĵ

-0.25

 Political

-0.25

å¤ĸ

-0.24

TexImage

-0.24

 trad

-0.24

éļľç¢į

-0.23

IRA

-0.23

POSITIVE LOGITS

éĩįåŀĭ

0.29

 Ravens

0.27

ulance

0.27

çīĩ

0.26

ungi

0.25

.folder

0.25

-Un

0.24

åİ¢

0.24

@g

0.24

Solid

0.23

Activations Density 0.004%