INDEX

Explanations

Unstructured text snippets

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

åŁºç¡Ģ

-0.31

ä¸Ģç§į

-0.29

po

-0.27

æĥħåĨµä¸ĭ

-0.26

åŁºç¡Ģä¸Ĭ

-0.26

ä¸¤ç§į

-0.26

lear

-0.25

rim

-0.25

fore

-0.25

if

-0.25

POSITIVE LOGITS

ustrial

0.27

ä¹Łç®Ĺæĺ¯

0.26

ustry

0.25

Ð½Ð°ÐºÐ¾

0.25

 enactment

0.25

èµĦæºĲéħįç½®

0.25

 Kavanaugh

0.24

upply

0.24

amina

0.24

zzle

0.24

Activations Density 0.001%