INDEX

Explanations

meeting, dealing, undercover, sale

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

ždý

-1.45

髣

-1.21

名が

-1.21

 бъ

-1.20

ったり

-1.16

ताओं

-1.16

isor

-1.16

בעת

-1.15

 incluidas

-1.15

 xvii

-1.15

POSITIVE LOGITS

1.85

an

1.20

for

1.16

curkan

1.09

out

1.06

rodz

1.06

 quicker

1.05

CUIT

1.04

 some

1.02

我和

1.02

Activations Density 0.021%