INDEX

Explanations

first names followed by surnames

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

source

0.73

 subtle

0.73

self

0.71

object

0.70

$/

0.65

 source

0.65

output

0.65

index

0.64

config

0.62

POSITIVE LOGITS

 Miller

1.23

 Kennedy

1.23

 Jones

1.22

 Baker

1.21

 Lopez

1.19

 Hernandez

1.18

 Springsteen

1.17

 Rodriguez

1.16

<unused1091>

1.15

 Armstrong

1.15

Activations Density 0.194%