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

æĮ¡

-0.28

itter

-0.26

 downt

-0.26

_permalink

-0.25

 Ø´Ùĥ

-0.25

ìľĹ

-0.25

å¹²

-0.25

presso

-0.24

ä¸įçĶ¨

-0.24

åİĭ

-0.24

POSITIVE LOGITS

 word

0.26

headline

0.26

 Chap

0.25

↵   ↵

0.24

SSI

0.24

aption

0.23

,rp

0.23

 Burg

0.23

fung

0.23

ä¾¿æ°ĳ

0.23

Activations Density 0.108%

No Known Activations

This feature has no known activations.