INDEX

Explanations

questions about understanding

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

 restores

1.70

 puterea

1.70

ָד

1.69

ﻼ

1.69

 следующее

1.61

ᴇ

1.60

 colocadas

1.60

 halen

1.59

dick

1.58

 суд

1.57

POSITIVE LOGITS

ت

2.47

та

2.36

ی

1.86

()=>{

1.80

ለያዩ

1.63

ㅎ

1.62

𝚖

1.59

𝚝

1.57

../../

1.57

ты

1.56

Activations Density 0.000%