INDEX

Explanations

name, label, title values

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

 myosin

1.43

 mutant

1.36

)}+\

1.30

 crianças

1.29

roidery

1.27

Hir

1.26

estan

1.24

 theseKeys

1.24

ствий

1.23

Puede

1.23

POSITIVE LOGITS

uig

1.61

 וש

1.46

ס

1.39

ovaný

1.33

ఝ

1.21

immediate

1.21

cích

1.19

𝘰

1.18

cję

1.17

𝘨

1.17

Activations Density 0.002%