INDEX

Explanations

phrases indicating probability

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

 Apparently

1.71

 apparently

1.61

 ممکن

1.55

Apparently

1.49

apparently

1.46

 presumably

1.46

可能是

1.42

 posiblemente

1.41

仿佛

1.40

似乎

1.39

POSITIVE LOGITS

 scenario

1.21

 arī

1.12

 some

1.06

 ilang

1.05

 algún

1.01

 όχι

1.01

 sensing

0.99

 bientôt

0.97

有不少

0.95

ずっと

0.94

Activations Density 0.093%