INDEX

Explanations

tuples, lists, data structures

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

 illuminate

1.37

in

1.33

 utilisent

1.32

在

1.30

 situés

1.24

Kako

1.23

 neumáticos

1.23

 enquête

1.20

 invade

1.18

нага

1.18

POSITIVE LOGITS

ali

1.86

dı

1.44

지

1.43

1.41

1.35

gt

1.33

िन

1.30

di

1.27

are

1.27

dt

1.26

Activations Density 0.001%