INDEX

Explanations

mathematical notation and code snippets

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

ftance

-0.73

 опять

-0.73

тельность

-0.73

enthusi

-0.73

 onyx

-0.72

tish

-0.71

%/

-0.71

gov

-0.70

strategies

-0.70

үү

-0.70

POSITIVE LOGITS

_{

1.67

1.53

<sub>

1.52

}_

1.30

1.20

_{

1.17

'_

1.16

＿

1.08

}_{

1.06

*_

1.05

Activations Density 0.050%