INDEX

Explanations

comparisons with than

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

weiß

-1.63

 Terkait

-1.58

lyd

-1.54

 recomendar

-1.54

");

-1.52

because

-1.48

Комментарии

-1.48

 drenaje

-1.47

 calentamiento

-1.47

gaven

-1.46

POSITIVE LOGITS

how

1.96

 what

1.93

er

1.77

we

1.70

you

1.69

1.68

neling

1.58

を使用した

1.57

 have

1.57

を使用

1.54

Activations Density 0.032%