INDEX

Explanations

web links and contact info

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

 kafe

-0.90

 fotograf

-0.90

became

-0.87

OMEN

-0.86

 diber

-0.85

蝼

-0.81

ض

-0.80

 masquer

-0.79

muz

-0.79

нья

-0.78

POSITIVE LOGITS

 Contact

1.20

 https

1.16

 contact

1.15

https

1.14

 visit

1.14

Contact

1.13

 Address

1.06

contact

1.02

 Visit

1.01

Address

0.97

Activations Density 0.041%