INDEX

Explanations

test cases and code structures

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

was

-1.38

 venice

-1.37

ienė

-1.34

 dimen

-1.30

 enorm

-1.30

rror

-1.29

ですし

-1.28

is

-1.28

 cory

-1.27

 aste

-1.24

POSITIVE LOGITS

・・・・・

1.70

～

1.62

 lumière

1.56

僱

1.38

・・・・・・・・

1.37

･･

1.36

毎回

1.36

来说

1.33

･･･

1.32

 chacun

1.31

Activations Density 0.012%