INDEX

Explanations

code, docs, locations

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

edList

-0.27

ab

-0.27

çĹ¨

-0.26

bli

-0.25

åĨ»

-0.25

åĪĹ

-0.25

-letter

-0.25

imity

-0.25

 trainable

-0.24

æĹıèĩªæ²»

-0.24

POSITIVE LOGITS

 maxlen

0.29

ZN

0.28

 maxWidth

0.28

LTC

0.27

llx

0.26

 presses

0.26

orton

0.26

æľĢå¤§

0.26

inden

0.25

 Ð¼Ð°ÐºÑģÐ¸Ð¼Ð°Ð»ÑĮ

0.25

Activations Density 0.101%