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

èħĨ

-0.27

/documentation

-0.26

UNUSED

-0.25

 Panama

-0.25

å±ķå¼Ģ

-0.24

thed

-0.24

 sweetness

-0.24

gings

-0.24

/mp

-0.23

rots

-0.23

POSITIVE LOGITS

ilde

0.32

çĶ¸

0.28

azon

0.27

azo

0.26

az

0.26

ented

0.26

 labeled

0.25

ãĤ¤ãĥĪ

0.24

èĬİ

0.24

 Liberty

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.