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

odem

-0.29

RIX

-0.28

ä½Ĺ

-0.27

å¥Ń

-0.27

riot

-0.27

æĦıå¤§

-0.26

çļĦè¡¨æĥħ

-0.26

Experiment

-0.25

 Argument

-0.25

æºª

-0.24

POSITIVE LOGITS

 hope

0.26

te

0.25

ÑĨÐµÐ¿

0.24

usercontent

0.24

 Ð½ÐµÐ³Ð¾

0.24

lu

0.23

ä¸ĵäºº

0.23

ker

0.23

GLE

0.23

queued

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.