INDEX

Explanations

observe, watch, notice, view

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

 👀

2.16

сці

1.80

 pathologist

1.61

ర్

1.59

 подрост

1.52

withtag

1.52

ні

1.51

infected

1.51

 glimpses

1.42

 والذي

1.41

POSITIVE LOGITS

é

1.93

要知道

1.92

ست

1.91

queleto

1.78

完善

1.75

，

1.68

看起来

1.64

czy

1.63

،

1.63

看起來

1.61

Activations Density 0.496%