INDEX

Explanations

requests for explicit or graphic sexual content.

designed to, trained by

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

 која

0.17

 Dacă

0.17

😚

0.16

 Einwill

0.16

 Bhub

0.16

 озеро

0.16

ätz

0.16

('*

0.15

avaş

0.15

 ఉత్ప

0.15

POSITIVE LOGITS

by

0.38

 oleh

0.28

in

0.28

for

0.25

 into

0.25

by

0.25

 توسط

0.24

 from

0.21

 with

0.21

in

0.20

Activations Density 0.734%