INDEX

Explanations

individual responsibility and choice

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

 mama

1.16

 shitty

1.10

 nigga

1.07

 yeah

1.02

dry

1.01

 crappy

0.98

 messed

0.95

 halloween

0.95

winding

0.95

 Halloween

0.94

POSITIVE LOGITS

 нередко

1.66

 perlu

1.61

 рекомендуется

1.58

也可

1.57

を有する

1.56

 によ

1.52

лід

1.51

 ماہر

1.51

 電気

1.50

此外

1.47

Activations Density 0.239%