INDEX

Explanations

make claims, make a mess, make a name

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

赑

-1.71

ી

-1.49

謦

-1.46

for

-1.45

-1.44

图为

-1.40

IZING

-1.37

’

-1.31

 таким

-1.30

还是很

-1.30

POSITIVE LOGITS

 régal

1.98

 rafraî

1.77

 étan

1.70

 dodatk

1.59

 refroid

1.56

 tuyau

1.52

 dvě

1.50

杙

1.48

 levier

1.48

uscita

1.45

Activations Density 0.045%