INDEX

Explanations

specific compound phrases

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

administered

0.81

quantitative

0.80

opathological

0.80

administrative

0.77

composed

0.76

adrenergic

0.75

ocratic

0.75

 homogeneous

0.74

homogeneous

0.74

fabricated

0.74

POSITIVE LOGITS

 stuff

2.14

 Stuff

1.61

的东西

1.41

stuff

1.39

Stuff

1.39

 issues

1.39

 info

1.37

 stuffs

1.37

 items

1.35

的東西

1.26

Activations Density 0.931%