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

hot

-0.32

 drop

-0.29

hot

-0.28

ä¾

-0.27

 touch

-0.26

ho

-0.26

(IN

-0.25

urg

-0.25

 objective

-0.25

(in

-0.24

POSITIVE LOGITS

 Crowley

0.27

olate

0.27

FFE

0.26

gyr

0.26

UGHT

0.25

 Rockefeller

0.25

è´¶

0.25

CLUDE

0.25

/helper

0.25

ateful

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.