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

-toggle

-0.29

ä»Ģä¹Īåľ°æĸ¹

-0.28

agues

-0.28

æĥ³åĪ°

-0.28

æĹħéĢĶ

-0.27

ÑĤÐ¾Ð¼

-0.24

bat

-0.23

æĹħ

-0.23

bat

-0.23

agra

-0.23

POSITIVE LOGITS

irl

0.38

ç§»

0.30

ä¸ĢéĿ¢

0.28

cene

0.27

ison

0.27

elm

0.27

ä¸Ģé¡¿

0.27

éĺ¿æ£®

0.26

IRM

0.26

 shift

0.26

Activations Density 0.010%

No Known Activations

This feature has no known activations.