INDEX

Explanations

D

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

cente

-0.28

nef

-0.26

gra

-0.25

bow

-0.25

sul

-0.25

 grazing

-0.25

onor

-0.24

efs

-0.24

 compared

-0.24

.deleteById

-0.24

POSITIVE LOGITS

æĪĸèĢħ

0.49

æĪĸåħ¶ä»ĸ

0.45

 æĪĸ

0.44

æĪĸæĺ¯

0.42

æĪĸèĢħåħ¶ä»ĸ

0.42

åı¦ä¸Ģç§į

0.41

æĪĸ

0.40

æĪĸèĢħæĺ¯

0.39

æĪĸå¤ļ

0.38

 vagy

0.38

Activations Density 0.081%