INDEX

Explanations

TV channels and stations

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

 españolas

-0.73

 Innoc

-0.73

NPR

-0.72

IEEE

-0.69

Imgur

-0.67

コンテンツ

-0.65

trap

-0.65

 카드

-0.64

UNIFIED

-0.64

پ

-0.64

POSITIVE LOGITS

 channel

1.86

 Channel

1.77

Channel

1.51

 channels

1.50

channel

1.40

 Canal

1.33

 Channels

1.28

Channels

1.27

CHANNEL

1.22

 canal

1.19

Activations Density 0.036%