INDEX

Explanations

spider/web

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

æ£ł

-0.29

ä¸Ľ

-0.27

åĨ¶

-0.25

tega

-0.24

edo

-0.23

Ð¾Ð±ÑĢÐ°Ð·

-0.23

abar

-0.23

endar

-0.23

ç§§

-0.23

CellStyle

-0.23

POSITIVE LOGITS

æįķ

0.34

ulatory

0.31

fw

0.30

 catcher

0.29

 capture

0.28

éªĻ

0.28

capture

0.27

 sticky

0.27

çĵ¶é¢Ī

0.27

ç³¯ç±³

0.27

Activations Density 0.885%