INDEX

Explanations

technical texts

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

 sure

-0.29

ä»¥ä¸º

-0.28

metric

-0.27

ejs

-0.26

jej

-0.26

 Towers

-0.26

åıĺéĢŁ

-0.25

å±Ĳ

-0.25

oub

-0.25

neau

-0.24

POSITIVE LOGITS

yle

0.26

alley

0.26

DW

0.25

èį»

0.25

bite

0.24

Ð¸ÑĢÐ¾Ð²ÐºÐ¸

0.24

 advertiser

0.23

 bite

0.23

 Stark

0.23

Indent

0.23

Activations Density 0.176%