INDEX

Explanations

don't

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

prises

-0.07

kra

-0.07

 tick

-0.07

ije

-0.06

umin

-0.06

èĢĮè¨Ģä¹ĭ

-0.06

ellaneous

-0.06

ä¸¤æĹģ

-0.06

ãģ³

-0.06

å¤ªé«ĺ

-0.06

POSITIVE LOGITS

×Ļ×ľ×ķ×ª

0.09

illot

0.09

 DISCLAIMER

0.08

åĪ°æĤ¨çļĦ

0.07

æľīç»ıéªĮ

0.07

rs

0.07

 Macros

0.07

 ÑĥÑģ

0.07

ãģĳãģ©ãģŃ

0.07

æĻ¨æĽ¦

0.07

Activations Density 0.115%