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

åİĭ

-0.26

åĨħéĻĨ

-0.25

 Press

-0.25

Press

-0.25

Rc

-0.24

key

-0.24

:key

-0.24

 Bris

-0.24

 Conspiracy

-0.24

æļ´åĬĽ

-0.24

POSITIVE LOGITS

 triplet

0.26

udev

0.25

éĢļ

0.25

Attention

0.25

éħĲ

0.24

-sp

0.24

-prepend

0.23

åĹĮ

0.23

umes

0.23

weakSelf

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.