INDEX

Explanations

adjectives describing categories

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

its

1.73

1.72

 einen

1.68

an

1.66

 sebuah

1.60

 eine

1.59

它

1.57

is

1.54

 isang

1.53

 seorang

1.50

POSITIVE LOGITS

都很

2.51

 كلهم

2.49

 những

2.47

들도

2.34

 كانوا

2.31

一个个

2.30

也都

2.24

 voltak

2.21

 đều

2.18

 themselves

2.17

Activations Density 0.705%