INDEX

Explanations

common English words

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĵĹ

-0.25

 landscape

-0.25

æĸ¹æ¡Ī

-0.25

otomy

-0.24

æ¾Ī

-0.24

ihan

-0.24

åĪĴ

-0.24

 folds

-0.23

Wh

-0.23

ÑģÑĤÐ°Ð²

-0.23

POSITIVE LOGITS

ç»ľ

0.29

æĿĤçī©

0.28

çº¹çĲĨ

0.28

åħ¬åı¸ç«łç¨ĭ

0.26

åŃĹåı·

0.25

.textColor

0.25

é¬ĥ

0.25

æľīçĶ¨çļĦ

0.25

éª¨å¤´

0.24

hon

0.24

Activations Density 0.001%