INDEX

Explanations

family members and relations

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

酛

0.56

 letzt

0.51

 aurait

0.51

 perturbative

0.50

 second

0.50

 orthodoxy

0.50

my

0.50

 heresy

0.50

 basic

0.50

 codebase

0.49

POSITIVE LOGITS

0.97

0.95

;:

0.93

including

0.91

 nombreux

0.88

 including

0.87

 সঞ্জ

0.85

 различ

0.84

:,

0.83

Viele

0.82

Activations Density 0.000%