INDEX

Explanations

numbers with decimal points

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

ت

1.96

تهم

1.59

 averaging

1.41

й

1.38

是从

1.37

 demean

1.35

是很

1.34

т

1.33

 certes

1.32

 downside

1.31

POSITIVE LOGITS

een

2.50

ní

1.91

卦

1.83

्स

1.76

ো

1.72

cle

1.71

во

1.71

ுக

1.70

ieth

1.65

eenth

1.63

Activations Density 0.235%