INDEX

Explanations

`selector:` followed by component name

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

কর

1.68

yzed

1.63

ுக்

1.47

 reconoc

1.37

edì

1.34

琟

1.32

teri

1.31

zés

1.28

 commutative

1.26

 reverb

1.25

POSITIVE LOGITS

étais

1.56

ो

1.50

 Honestly

1.43

aan

1.41

 flocked

1.41

 subsided

1.38

 yerde

1.37

inside

1.37

स्थित

1.34

illing

1.34

Activations Density 0.000%