INDEX

Explanations

mathematical or programming code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ÐĲÐ»ÐµÐºÑģÐ°Ð½

-0.27

 ÐĶÐ¼Ð¸ÑĤÑĢ

-0.24

æĪĲåĵģ

-0.22

 ÐĶÐ¼

-0.21

ä¸Ģä¼ļ

-0.20

æĲº

-0.20

ä¸Ŀ

-0.20

orer

-0.20

å¯¹ä»ĺ

-0.20

auga

-0.19

POSITIVE LOGITS

æĪĸå°Ĩ

0.19

ÑĢÑĥÐ¶

0.19

ÐµÐ½

0.18

æĤ£ä¸Ĭ

0.18

ÑĩÑĥÐ²

0.17

 nipples

0.17

èķŀ

0.17

æĤ£æľī

0.17

èİ²

0.17

å²Ĳ

0.17

Activations Density 0.111%