INDEX

Explanations

drawings or art creation

finds tokens that introduce or mark major sections/paragraphs — i.e., heading- or topic-introducing words used in explanatory or structured informational text.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

udf

0.46

শিক্ষ

0.41

Goed

0.41

 табле

0.40

Mission

0.39

 উত্প

0.38

院校

0.38

 اتا

0.37

但也

0.37

 tiếng

0.37

POSITIVE LOGITS

 drawings

0.46

یا

0.43

hanti

0.42

цима

0.41

 Drawings

0.40

 Draws

0.39

ahorse

0.39

یم

0.38

𝔦

0.38

skins

0.38

Activations Density 0.152%