INDEX

Explanations

"Hello" followed by punctuation or "from"

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

𝖑

2.70

2.63

𝖘

2.51

𝚝

2.39

েনারেল

2.37

𝖓

2.31

𝖙

2.26

𝚔

2.10

yed

2.08

 Xác

2.08

POSITIVE LOGITS

jest

1.92

 marketable

1.74

eel

1.67

о

1.65

poison

1.59

snake

1.58

 obstante

1.56

Marble

1.55

없는

1.54

 conscious

1.51

Activations Density 0.000%