INDEX

Explanations

line breaking and text wrapping

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

ആ

0.40

 Westminster

0.38

subTest

0.38

iela

0.38

 ప్రత్యేక

0.37

 හර

0.37

ಆ

0.36

bc

0.36

 ప్రత్య

0.36

飽

0.36

POSITIVE LOGITS

 penalties

0.61

 stretch

0.60

 tolerance

0.59

 tolerant

0.58

 violators

0.58

Tolerance

0.58

 toler

0.56

 Tolerance

0.55

 overflows

0.55

 stretchy

0.55

Activations Density 0.002%