INDEX

Explanations

within or into sentences

categories colonialism attempt categories

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 Velcro

0.43

 bumps

0.41

 emission

0.38

 descent

0.37

 medial

0.37

椅子

0.37

]=

0.36

 पीड

0.36

 obedience

0.36

 racer

0.36

POSITIVE LOGITS

SalesReport

0.51

🥭

0.51

FTWARE

0.49

 اكثر

0.49

GITHUB

0.49

銷

0.48

ضي

0.47

當年

0.47

ATE

0.46

 שלו

0.46

Activations Density 0.000%