INDEX

Explanations

requests, instructions

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

cing

-0.29

ful

-0.28

Ð¾ÑģÑĤÐ¸

-0.28

å¾Ĺ

-0.27

Ful

-0.27

éĻħ

-0.27

idd

-0.27

aire

-0.26

asion

-0.26

ion

-0.25

POSITIVE LOGITS

æĥ³åĬŀæ³ķ

0.28

 encour

0.28

ä¸ºåĩĨ

0.26

èŃ¦

0.26

leta

0.25

é¼ĵåĬ±

0.25

ä¸įè¦ģåĨį

0.25

 landlord

0.24

æ²³è¥¿

0.24

.parseFloat

0.24

Activations Density 0.007%