INDEX

Explanations

scientific notation powers of 10

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

יות

2.95

儡

2.74

ताई

2.64

ndan

2.33

سازی

2.29

 pecans

2.26

 MSCI

2.26

 fences

2.26

 تنظيم

2.20

الله

2.20

POSITIVE LOGITS

نه

3.00

ときは

2.77

و

2.74

ve

2.71

いない

2.68

ו

2.62

д

2.61

حال

2.44

cludes

2.43

 cout

2.41

Activations Density 0.036%