INDEX

Explanations

mathematical contexts with `in`

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

在乎

-0.93

 counterpart

-0.87

ash

-0.81

では

-0.80

腾

-0.78

 einzelnen

-0.78

への

-0.77

 многие

-0.77

 Vols

-0.77

 جاء

-0.77

POSITIVE LOGITS

んですね

1.02

between

1.01

Poznám

0.93

꿩

0.92

 maravillosa

0.91

：

0.91

んですよね

0.90

nungen

0.90

σμα

0.89

ůvod

0.88

Activations Density 0.024%