INDEX

Explanations

public statements and rhetoric

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

æĢĢçĿĢ

-0.23

åŃĺåľ¨äºİ

-0.22

æľīå¹¸

-0.21

ä»İå°ı

-0.21

æīĭèīº

-0.20

æĬ¥éħ¬

-0.19

_cases

-0.19

åĽłä¸ºæĪĳ

-0.19

ctest

-0.19

äº²çľ¼

-0.18

POSITIVE LOGITS

åı£å¾Ħ

0.30

åħ¬å¼Ģ

0.29

è¨Ģè®º

0.26

 publicly

0.26

 statements

0.26

å¯¹å¤ĸ

0.26

 rhetoric

0.24

emean

0.24

 ÐºÐ½Ð¾Ð¿Ðº

0.24

ç«ĭåľº

0.23

Activations Density 0.096%