INDEX

Explanations

No Explanations Found

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

<Tag

-0.30

 Moderator

-0.29

çĬį

-0.27

TAG

-0.26

ä¸ĳ

-0.26

TAG

-0.26

è¿ĩåħ³

-0.25

 Ð¿Ð°ÑĢÐ°

-0.25

ALAR

-0.24

ä¾Ľæ±Ĥ

-0.24

POSITIVE LOGITS

à¸£à¸Ńà¸ļ

0.27

 tele

0.27

æ³¨æĦıåĪ°

0.26

å¯°

0.25

tele

0.25

æİ¥åħ¥

0.25

 Besch

0.24

 instead

0.24

cos

0.24

Ã¼ck

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.