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

ogle

-0.28

ä¹ħäºĨ

-0.27

æ²Ł

-0.27

ä¸įçĦ¶

-0.26

-tm

-0.26

ä¸ĬæĿ¥

-0.26

nette

-0.25

uncture

-0.25

æºĲæ³ī

-0.25

æĭĴ

-0.25

POSITIVE LOGITS

 fraction

0.25

ahi

0.24

"|

0.24

Fraction

0.24

lass

0.24

iben

0.24

ablish

0.23

 ÏĢ

0.23

akes

0.23

DEFINED

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.