INDEX

Explanations

determiners (a, an, one)

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

 things

1.05

things

0.86

 coisas

0.77

 obvious

0.72

 cosas

0.71

we

0.71

ения

0.70

が決

0.70

 dolayı

0.70

 सबकुछ

0.68

POSITIVE LOGITS

 Sebuah

1.69

 sebuah

1.64

 another

1.45

是一個

1.45

 Another

1.44

another

1.44

一種

1.43

Another

1.40

这是一个

1.39

 isang

1.36

Activations Density 0.946%