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

 ingredient

-0.31

æľĢåĲİä¸Ģæ¬¡

-0.30

ingredient

-0.26

é½Ĳèģļ

-0.26

æķ£

-0.25

 swallowing

-0.25

åĺĺ

-0.25

è½Ń

-0.25

ä¿ĺ

-0.25

brief

-0.25

POSITIVE LOGITS

irate

0.29

ermo

0.28

fir

0.26

GOOD

0.26

eko

0.25

èĬĤ

0.25

 marks

0.24

 mark

0.24

åį¸

0.24

town

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.