INDEX

Explanations

common examples

expository structural and formatting cues that organize text into sections, lists, headings, and step‑by‑step breakdowns.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 прият

0.50

 સંપૂર્ણ

0.48

ктак

0.46

〢

0.44

 зах

0.44

 angene

0.44

újt

0.43

 облег

0.43

 שלך

0.43

 переза

0.43

POSITIVE LOGITS

 historical

0.66

 historically

0.63

 Historically

0.59

 examples

0.59

 known

0.57

 moderne

0.57

Historically

0.57

 известные

0.57

 scientific

0.56

 conocido

0.56

Activations Density 0.259%