INDEX

Explanations

pop up, in, out, into

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

ри

1.42

ารย์

1.41

нию

1.39

я

1.27

 Michaelmas

1.23

йки

1.23

scaping

1.23

ريق

1.15

не

1.15

سة

1.14

POSITIVE LOGITS

 levelled

1.69

 대해

1.62

 대해서

1.62

 molds

1.61

isActive

1.59

 schematically

1.56

надцать

1.55

 autopilot

1.53

 대하여

1.52

zahlen

1.52

Activations Density 0.006%