INDEX

Explanations

donating or donations

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

ása

-1.18

ﾞ

-1.17

ut

-1.14

st

-1.09

émoc

-1.05

 englischen

-1.01

MING

-0.98

えた

-0.98

擁有

-0.98

動物

-0.98

POSITIVE LOGITS

to

1.69

 towards

1.43

toward

1.30

towards

1.26

 toward

1.25

 Towards

1.19

ckles

1.07

eggs

1.02

 Toward

0.96

Towards

0.94

Activations Density 0.013%