INDEX

Explanations

questions or descriptions

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

<unused2197>

0.99

<unused1408>

0.97

<unused1612>

0.96

<unused2221>

0.95

<unused2223>

0.93

<unused450>

0.90

 SalesLT

0.89

<unused1480>

0.88

 vaginale

0.88

<unused1996>

0.87

POSITIVE LOGITS

 .....

1.48

.....

1.47

 ....

1.34

....

1.34

???

1.31

？？

1.29

?...

1.24

????

1.23

 consideration

1.23

?:

1.23

Activations Density 0.541%