INDEX

Explanations

Uncertainty and code

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

 guess

-1.16

binant

-0.91

 AssemblyCulture

-0.84

 ujednoznacz

-0.78

 kasarigan

-0.77

 fallu

-0.76

LookAnd

-0.75

MemoryWarning

-0.74

 Wiktionnaire

-0.68

 baptized

-0.68

POSITIVE LOGITS

ses

0.57

ness

0.54

wear

0.53

san

0.51

sal

0.50

sport

0.50

sa

0.50

livan

0.49

mer

0.49

Activations Density 0.216%