INDEX

Explanations

requests for actions or content that violate safety and ethical guidelines.

after these words

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

or

0.21

0.20

ers

0.19

0.18

或其他

0.18

 Inoltre

0.18

<unused2117>

0.18

);

0.18

；

0.18

ook

0.17

POSITIVE LOGITS

0.27

 bagaimana

0.25

 trying

0.24

 wanting

0.24

 getting

0.24

 faptul

0.23

 finding

0.23

an

0.23

trying

0.23

 BEING

0.23

Activations Density 3.036%