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

æ·±æ·±çļĦ

-0.28

isex

-0.28

 hipp

-0.27

/off

-0.27

 reproduction

-0.27

 nicely

-0.26

çĹŀ

-0.26

forder

-0.26

æļ¨

-0.25

-May

-0.25

POSITIVE LOGITS

occ

0.27

ools

0.25

ductor

0.25

uju

0.25

ç©°

0.24

æŀģ

0.24

emplates

0.24

excel

0.24

erras

0.24

ÙĦØª

0.24

Activations Density 0.005%

No Known Activations

This feature has no known activations.