INDEX

Explanations

foreign languages

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

çľĭ

-0.28

aar

-0.27

 Horde

-0.25

beth

-0.25

roman

-0.25

ressive

-0.25

jug

-0.25

æīĢæľīæĿĥ

-0.24

ogi

-0.24

å·¥ä½ľç«Ļ

-0.24

POSITIVE LOGITS

Äĩ

0.40

cio

0.31

Äĩe

0.31

ÑĽ

0.30

Äĩi

0.29

cial

0.28

 switch

0.28

switch

0.28

olio

0.27

Å¥

0.26

Activations Density 0.916%