INDEX

Explanations

audience viewers listeners

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

Developers

-0.82

 warriors

-0.82

 Operators

-0.82

genomen

-0.79

anin

-0.74

dbg

-0.74

 missionaries

-0.73

 proteine

-0.72

Warriors

-0.72

 Supplier

-0.72

POSITIVE LOGITS

 viewers

6.13

 audience

5.88

 audiences

5.28

 viewer

4.72

 listeners

4.34

audience

4.28

viewers

4.06

观众

3.91

 Audience

3.67

Audience

3.63

Activations Density 0.139%