INDEX

Explanations

explains or defines

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

 hadn

1.41

だったので

1.32

だな

1.29

ありがとうございました

1.28

でした

1.27

 failed

1.22

 Went

1.22

 prochaine

1.22

 hade

1.21

さすが

1.20

POSITIVE LOGITS

是指

2.78

 genellikle

2.25

 일반적으로

2.24

 terdiri

2.21

可以是

2.20

指的是

2.19

이란

2.19

usually

2.12

 consiste

2.11

 désigne

2.07

Activations Density 0.313%