INDEX

Explanations

questions and code snippets

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

in

-2.36

but

-2.33

if

-2.22

 dikutip

-2.00

 Noruega

-1.94

 During

-1.90

 when

-1.89

ؾ

-1.87

вать

-1.87

琑

-1.84

POSITIVE LOGITS

 которы

2.28

⚌

2.09



1.91

 кото

1.86

 DOES

1.80

 sauvages

1.79

蹑

1.77

 mourir

1.74

1.71

 provoquer

1.71

Activations Density 0.000%