INDEX

Explanations

introduction to summary tables

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*\

1.17

tokenizer

1.15

1.12

ியை

1.10

*@

1.10

*,

1.08

]*

1.06

*>

1.04

**/

1.02

,*

1.01

POSITIVE LOGITS

 صدیق

0.80

 ఎన్నిక

0.77

 However

0.74

ል።

0.73

However

0.73

}^{

0.72

лік

0.69

 Sentinel

0.69

 frogs

0.69

❦

0.69

Activations Density 0.016%