INDEX

Explanations

pyramid shape or scheme

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

이

2.88

я

2.46

ে

2.44

 conformations

2.44

 называют

2.40

ing

2.29

bied

2.21

ozygous

2.20

 netizens

2.20

jne

2.18

POSITIVE LOGITS

ده

1.83

ما

1.76

1.74

лекет

1.71

COP

1.68

دي

1.67

 gada

1.64

بیل

1.62

ératures

1.61

Hak

1.60

Activations Density 0.003%