INDEX

Explanations

converted, acting, transformed

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 restorations

0.43

 التعامل

0.40

 exist

0.38

 दस्तक

0.36

fif

0.36

 dominion

0.36

 wheelchairs

0.36

 Tsuen

0.36

与之

0.36

 exists

0.35

POSITIVE LOGITS

 dijadikan

1.01

 convertido

0.90

 acting

0.89

 converted

0.88

 превра

0.88

 Acting

0.86

 repurposed

0.86

Acting

0.84

 convertirse

0.82

 تبدیل

0.80

Activations Density 0.000%

No Known Activations