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

untu

-0.28

chter

-0.28

åħļæĶ¿

-0.27

ajo

-0.27

à¤¢

-0.27

Kes

-0.26

çªģ

-0.26

ãĥĥãĥī

-0.25

ongs

-0.25

çªģå¦Ĥ

-0.24

POSITIVE LOGITS

 Sinai

0.28

hell

0.28

æ³¨è§Ĩ

0.26

çļĦæľīæķĪ

0.25

 grilled

0.25

æľīæķĪ

0.25

itm

0.25

hill

0.24

èĵ¼

0.24

è¿Ļä¸ªè¡Įä¸ļ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.