INDEX

Explanations

examples, explanations, or specific groups

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

kannya

1.02

">{{

0.96

 Поэтому

0.93

 этому

0.92

 здесь

0.91

״

0.91

 इसमें

0.90

৷

0.90

 şeyler

0.89

Vì

0.86

POSITIVE LOGITS

이나

1.26

ங்கிணை

1.19

 supuesto

1.18

ay

1.17

 welchem

1.12

sembled

1.11

 whom

1.09

то

1.08

 cooked

1.07

すなわち

1.06

Activations Density 0.207%