INDEX

Explanations

detecting fake or hateful content

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

ar

1.55

ez

1.30

es

1.22

ため

1.16

ea

1.15

er

1.14

as

1.13

acoli

1.10

lighting

1.08

iéndose

1.07

POSITIVE LOGITS

 ओम

1.30

 structs

1.29

 straining

1.29

 cherish

1.25

 cues

1.24

 inception

1.22

 onset

1.20

 trouble

1.19

 undercut

1.18

 adhering

1.16

Activations Density 0.001%