INDEX

Explanations

after work or daily routine

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

ignon

-0.29

éĻĲæľŁ

-0.25

åħ¬çĦ¶

-0.24

åĿļå®ļä¸įç§»

-0.24

å½ĵåį³

-0.24

è°ĭ

-0.24

 zeroes

-0.24

 PropTypes

-0.23

é¢ĳéģĵ

-0.23

 outright

-0.23

POSITIVE LOGITS

ç´¯äºĨ

0.42

çĸ²æĥ«

0.39

æĻļä¸Ĭ

0.35

çĸ²åĬ³

0.35

çĸ²

0.33

ä¸ĭçıŃ

0.32

æĥ«

0.30

åĬ³ç´¯

0.30

 ä¸ĭåįĪ

0.30

ä¸ĬåįĪ

0.30

Activations Density 0.036%