INDEX

Explanations

and

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

 gebruiken

-0.73

 används

-0.71

 digunakan

-0.69

 verwendet

-0.68

 brukes

-0.64

 used

-0.64

 usarlo

-0.62

used

-0.62

enumii

-0.60

"));

-0.60

POSITIVE LOGITS

 SwitchCompat

0.59

LookAnd

0.54

 محفوظة

0.49

oprecipitation

0.48

 Presses

0.48

tedrale

0.47

 caches

0.47

RunWith

0.46

 Dostupné

0.46

 undergo

0.46

Activations Density 0.066%