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

away

-0.31

ennie

-0.29

led

-0.29

ç»¿èī²åıĳå±ķ

-0.26

åģľçķĻ

-0.26

Away

-0.25

illary

-0.24

Defines

-0.24

pile

-0.23

food

-0.23

POSITIVE LOGITS

erd

0.28

orr

0.27

 posed

0.26

statt

0.25

ekt

0.25

liner

0.25

 pratique

0.24

 Affero

0.24

corr

0.24

ç§ģç«ĭ

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.