INDEX

Explanations

Code-related

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

quete

-0.30

resent

-0.29

 conceded

-0.28

UEL

-0.27

/Area

-0.27

ACY

-0.26

cosystem

-0.25

 thá»¥

-0.25

raries

-0.25

 accept

-0.24

POSITIVE LOGITS

ized

0.42

ize

0.41

izing

0.38

izes

0.37

istically

0.36

istic

0.32

izer

0.28

å·¦

0.28

ie

0.27

izen

0.27

Activations Density 0.797%