INDEX

Explanations

slash followed by numbers

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

 voila

3.37

𝘵

3.07

ার

2.84

 volna

2.76

験

2.54

 நாட்கள்

2.48

𝘧

2.46

 būt

2.43

ካከል

2.40

 Oleh

2.35

POSITIVE LOGITS

-/-

2.89

 نحن

2.72

../

2.70

PRNewswire

2.69

 bilo

2.68

نك

2.55

../../

2.48

わからない

2.46

 willen

2.44

ि

2.43

Activations Density 0.234%