INDEX

Explanations

Nelson and associated entities

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

isotropic

3.28

cations

2.80

ে

2.63

ح

2.56

 convinced

2.47

cation

2.46

shader

2.44

메이션

2.42

 unquestionably

2.41

े

2.36

POSITIVE LOGITS

й

2.91

2.80

2.15

ка

2.14

 همچ

2.10

 सटे

2.09

 уж

2.05

ovo

2.03

 మంది

1.97

 रोक

1.96

Activations Density 0.001%