INDEX

Explanations

defamation libel slander smearing

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

Optim

0.49

 оптими

0.46

optim

0.45

索引

0.42

 entusi

0.41

 optim

0.41

 আধ

0.41

༄

0.40

 متجه

0.40

 Optim

0.40

POSITIVE LOGITS

 slander

1.76

 defamatory

1.58

 defamation

1.49

 smear

1.47

诽

1.44

 smears

1.38

 defam

1.33

 baseless

1.27

 libel

1.26

誣

1.23

Activations Density 0.050%