INDEX

Explanations

licensed or certified

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

anse

-0.25

",-

-0.24

ä¸įå¿ħ

-0.23

åıªéľĢ

-0.23

è¿İæĿ¥äºĨ

-0.22

whel

-0.22

æĢ§å¼º

-0.22

çĥĽ

-0.20

 proudly

-0.20

ä¸įè®ºæĺ¯

-0.20

POSITIVE LOGITS

èµ·çłģ

0.38

èĩ³å°ĳ

0.31

è¿ĺå¥½

0.29

proper

0.29

 properly

0.29

èĢĮæĺ¯

0.28

 atleast

0.27

æīįèĥ½

0.27

 ÑħÐ¾ÑĤÑı

0.27

åıĬæĹ¶

0.26

Activations Density 0.318%