INDEX

Explanations

explaining how something works

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

יות

1.89

ت

1.81

uating

1.50

ా

1.50

aient

1.49

ר

1.45

1.41

 been

1.41

𝐦

1.39

uates

1.38

POSITIVE LOGITS

Más

1.36

 proporciona

1.33

й

1.31

이션

1.29

Según

1.27

ところで

1.26

 übernahm

1.25

Modulo

1.24

 construire

1.24

 съем

1.21

Activations Density 0.036%