INDEX

Explanations

Certain followed by a type or category

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

iidae

1.77

ু

1.66

 gasket

1.64

એ

1.63

 Pohl

1.61

 Simplifying

1.59

endenti

1.59

 passiert

1.56

 Musicians

1.54

ेच्छा

1.53

POSITIVE LOGITS

ח

2.69

ت

2.58

یر

2.56

ע

2.39

mp

2.27

т

2.25

ە

2.23

מ

2.22

leri

2.20

짙

2.16

Activations Density 0.036%