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

iol

-0.29

æĹ¥ä¸ĭåįĪ

-0.27

 organ

-0.27

 Ã³rgÃ£o

-0.27

aden

-0.26

ernel

-0.26

osto

-0.25

 Organ

-0.25

ado

-0.25

èħº

-0.25

POSITIVE LOGITS

ÐµÐ²Ð¸Ñĩ

0.27

ä¿³

0.25

lazy

0.25

 Crowd

0.24

 disbelief

0.24

selectAll

0.24

éªĨ

0.24

 Simulation

0.24

Twig

0.24

 trench

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.