INDEX

Explanations

single letters including Greek/Cyrillic

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

öt

0.27

ío

0.25

män

0.25

izuje

0.24

idade

0.24

idad

0.24

そこで

0.24

렀

0.23

uidado

0.23

ếm

0.23

POSITIVE LOGITS

 trên

0.29

 balkon

0.25

 tục

0.24

薨

0.24

 ஏரா

0.24

 mellitus

0.24

 νέ

0.24

 enorme

0.24

 huge

0.23

 geométricas

0.23

Activations Density 0.003%