INDEX

Explanations

Mixed code and text

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mind

-0.55

mind

-0.51

 Mind

-0.51

 cores

-0.49

 core

-0.49

ễn

-0.48

core

-0.48

BITE

-0.47

 Force

-0.47

colgroup

-0.46

POSITIVE LOGITS

jooq

0.63

 dovuto

0.61

 Chwiliwch

0.59

oredCriteria

0.59

 ویکی‌پدی

0.59

ніципалі

0.55

ImageContext

0.55

 gradova

0.55

 يتيمه

0.54

wieś

0.54

Activations Density 0.000%