INDEX

Explanations

many/Most followed by nouns

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

另一种

1.89

ాత

1.81

ɴ

1.71

ה

1.65

 शादी

1.63

ului

1.62

একটি

1.58

 třeba

1.58

ulter

1.58

 میشه

1.55

POSITIVE LOGITS

ু

2.37

 people

2.11



2.02

ল

1.98

 semblance

1.97

 atvej

1.96

 cases

1.95

 lname

1.85

 хора

1.84

ب

1.81

Activations Density 0.108%