INDEX

Explanations

ellipsis

continuation or abstraction

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

<u>

0.68

<i>

0.61

Ꮨ

0.61

0.59

<em>

0.56

AND

0.56

 INCLUDING

0.53

½

0.52

indsight

0.52

<sub>

0.51

POSITIVE LOGITS

 […]

1.98

 [...]

1.79

[...]

1.69

[…]

1.59

...</

1.57

 阅读全文

1.51

...">

1.48

 \...

1.47

,...

1.36

 (...)

1.35

Activations Density 0.750%