INDEX

Explanations

technical/formal language

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

ann

-0.31

Ann

-0.30

Ann

-0.29

Lee

-0.28

halb

-0.27

æķĪçİĩ

-0.27

 Powers

-0.27

å·¥ä½ľæķĪçİĩ

-0.26

ann

-0.26

 reducers

-0.26

POSITIVE LOGITS

oteca

0.30

çķĻ

0.27

è¿Ļé¡¹

0.26

æĹ¥äº§

0.26

tags

0.25

reserve

0.25

æĴ°åĨĻ

0.25

 klar

0.25

azes

0.24

ä¸Ģå¹ħ

0.24

Activations Density 0.906%