INDEX

Explanations

serene or name endings ere/era

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

্লাহ

1.63

ם

1.40

ных

1.35

 blow

1.31

 blur

1.30

 hang

1.29

 modestly

1.29

此之外

1.28

ಿಕ

1.27

 Weights

1.23

POSITIVE LOGITS

л

2.48

ی

1.89

 alcuna

1.87

ে

1.87

ل

1.85

لا

1.82

ри

1.80

سی

1.76

 secretário

1.75

Nome

1.73

Activations Density 0.073%