INDEX

Explanations

referring to preceding text

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

ן

2.05

اً

1.88

ي

1.80

ל

1.77

ਾ

1.66

но

1.59

ро

1.59

ز

1.58

िता

1.54

ি

1.52

POSITIVE LOGITS

 reproach

1.61

GOD

1.52

以外の

1.48

 nacido

1.47

 concernant

1.40

 vrchol

1.38

нима

1.34

่

1.34

ंना

1.33

 ukaz

1.30

Activations Density 0.061%