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

è§Ħ

-0.27

imos

-0.26

 Pins

-0.26

incer

-0.26

 genu

-0.26

rig

-0.25

 nominate

-0.24

rending

-0.24

 herald

-0.24

infeld

-0.24

POSITIVE LOGITS

ãİľ

0.28

NEY

0.27

fax

0.26

cam

0.25

æīĵåħ¥

0.25

éħįåģ¶

0.25

ãİĿ

0.25

Targets

0.25

Il

0.25

âĬ¿

0.23

Activations Density 0.882%

No Known Activations

This feature has no known activations.