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

(tm

-0.28

èĤŁ

-0.28

asonry

-0.26

ä¹Ŀå¹´

-0.25

ë¦¿

-0.25

ntl

-0.24

 catholic

-0.24

.va

-0.23

åķĨ

-0.23

fri

-0.23

POSITIVE LOGITS

ead

0.29

æŀĲ

0.26

jay

0.25

æĳ©

0.25

lat

0.25

orld

0.25

)))),

0.24

éĻįåĪ°

0.24

Lat

0.24

 Authenticate

0.24

Activations Density 0.101%

No Known Activations

This feature has no known activations.