INDEX

Explanations

have access or information

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

 been

2.87

ﻤ

2.69

्ड

2.66

 BEEN

2.42

been

2.17

ve

2.16

 Been

2.15

dır

2.14

 subset

2.13

ﺠ

2.12

POSITIVE LOGITS

是非常

2.46

 fome

2.40

});

2.06

紝

2.02

'})

1.96

াল

1.93

𝓌

1.92

Require

1.89

 classificação

1.87

𝓀

1.86

Activations Density 0.058%