INDEX

Explanations

convicted of or guilty of

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

 semillas

0.45

 سری

0.44

 crap

0.41

 संके

0.41

ьи

0.39

 lccn

0.39

 ሁኔታ

0.39

と呼ば

0.38

Gag

0.38

classified

0.38

POSITIVE LOGITS

charges

0.67

 charges

0.65

Charges

0.63

 Charges

0.58

 chargé

0.54

 guilty

0.52

 chargée

0.52

 charging

0.50

Charge

0.50

 Charge

0.49

Activations Density 0.001%