INDEX

Explanations

not single or complex

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

 unconventional

0.43

 неста

0.41

 nontrivial

0.39

 unofficial

0.39

 profesional

0.37

 creative

0.36

 deeper

0.36

 hosting

0.36

uencia

0.35

ualitas

0.35

POSITIVE LOGITS

 rigid

1.41

 neat

1.41

 neatly

1.36

 rigidly

1.23

rigid

1.23

neat

1.15

 linear

1.14

 monolithic

1.13

 Rigid

1.13

 fixed

1.11

Activations Density 0.193%