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

 banged

-0.27

 bang

-0.27

Ä±ÄŁÄ±

-0.26

æĥ³èµ·æĿ¥

-0.26

ssi

-0.26

ridged

-0.26

è¯·å¤§å®¶

-0.26

ActionTypes

-0.25

ä¹ħ

-0.24

çĻ¾å¹´

-0.24

POSITIVE LOGITS

dev

0.28

æº¶

0.27

åĨ

0.27

åĨ¢

0.27

ç§ĳåŃ¦åıĳå±ķ

0.27

çĨĶ

0.27

èĩ£

0.26

—

0.25

table

0.25

 Grande

0.25

Activations Density 0.002%

No Known Activations

This feature has no known activations.