INDEX

Explanations

code structure components: Meta, Regex, mix

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

кі

1.02

ل

0.88

с

0.87

з

0.86

м

0.85

م

0.83

的方式

0.81

 例文帳に追加

0.81

েল

0.80

نون

0.77

POSITIVE LOGITS

 кусо

1.23

 должны

1.14

 इस्ती

1.12

뒤

1.09

 broadly

1.07

หมู่

1.04

 итоге

1.02

 serotonin

1.01

 dotycz

1.01

 повышение

1.01

Activations Density 0.000%