INDEX

Explanations

example of, if, necessary, those

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Укра

1.34

 кори

1.29

 любые

1.26

 обез

1.19

 Ци

1.18

 ligation

1.17

重視

1.17

 కూడా

1.16

У

1.13

 Пра

1.13

POSITIVE LOGITS

1.42

ी

1.35

કડ

1.23

्रेडिट

1.23

 tandem

1.21



1.19

 displacing

1.19

ن

1.18

atip

1.18

רץ

1.13

Activations Density 0.000%