INDEX

Explanations

sequence increments and ranges

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

 protects

0.43

 melindungi

0.43

 protect

0.41

 protective

0.41

Protect

0.39

楠

0.39

 PROTE

0.38

 breakage

0.37

 shielding

0.37

 किस्मत

0.37

POSITIVE LOGITS

 increment

0.69

 increments

0.65

 progressions

0.59

Increment

0.59

递

0.59

increment

0.58

 Increment

0.58

 Progression

0.58

 Iterator

0.56

 linearly

0.55

Activations Density 0.424%