INDEX

Explanations

generative"}, {"token": "generate"}

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

ם

1.06

to

1.01

ాలను

0.95

على

0.89

iv

0.87

هم

0.84

νο

0.83

কে

0.83

IP

0.79

ן

0.78

POSITIVE LOGITS

お客

1.02

یک

0.94

ام

0.91

 khác

0.91

 parfaitement

0.91

 інших

0.90

 dotycz

0.89

 italiane

0.86

 yazd

0.85

 centimetres

0.85

Activations Density 0.004%