INDEX

Explanations

Nouns followed by descriptions

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

 через

0.89

 Porque

0.83

 Where

0.82

 туда

0.82

是因为

0.82

Where

0.79

 이를

0.79

 Через

0.77

cuando

0.76

 მაშინ

0.74

POSITIVE LOGITS

 possessing

1.53

 whose

1.33

 having

1.30

 consisting

1.29

 boasting

1.27

 exhibiting

1.25

 undergoing

1.24

 offering

1.23

 containing

1.22

 providing

1.20

Activations Density 0.454%