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

 salads

-0.27

UBLIC

-0.26

ç±Ģ

-0.25

 ëį

-0.25

é¹ħ

-0.23

éĹ¨çªĹ

-0.23

 salad

-0.23

piece

-0.23

 Engel

-0.23

REP

-0.23

POSITIVE LOGITS

å¼ĤæĢ§

0.27

Ny

0.26

_REGISTRY

0.26

atches

0.25

romo

0.25

Manifest

0.25

.Messages

0.24

ingroup

0.23

 acceptable

0.23

æĳĺè¦ģ

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.