INDEX

Explanations

punctuation and code blocks

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

Kö

1.27

 tenemos

1.22

 hingegen

1.20

lt

1.11

 befindet

1.11

о

1.09

 preparada

1.07

 macht

1.06

 tengo

1.05

 umfasst

1.05

POSITIVE LOGITS

লোক

1.18

 glories

1.16

र

1.12

োজেন

1.10

য়াল

1.08

다른

1.07

杈

1.06

halation

1.03

!\!\

1.02

iin

1.01

Activations Density 0.001%