INDEX

Explanations

code snippets

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

äºĴè¡¥

-0.28

å½¢æĪĲ

-0.27

 coming

-0.27

Zi

-0.26

åĲī

-0.25

come

-0.25

htag

-0.24

æŃ£åľ¨

-0.24

coming

-0.24

lington

-0.24

POSITIVE LOGITS

 stubborn

0.25

 resistance

0.24

attack

0.24

æĬĹæĭĴ

0.24

ä¸įåħĭ

0.23

epend

0.23

 bread

0.23

æŃĥ

0.23

 Resistance

0.23

çĤ¯

0.23

Activations Density 0.882%