INDEX

Explanations

self-identification as Gemma

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

!,

1.00

<eos>

0.95

!;

0.92

!:

0.91

;,

0.90

-,

0.89

;)

0.85

 prevented

0.85

}:${

0.82

POSITIVE LOGITS

 Essentially

1.32

 Infine

1.27

Xinhua

1.25

Essentially

1.22

 Camin

1.21

Компания

1.21

 SURE

1.20

Дан

1.17

 Компания

1.17

 Hagan

1.15

Activations Density 0.166%