INDEX

Explanations

stu-dents, tional, tions

word endings

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

 […]

0.42

)–

0.38

 Limb

0.38

…”

0.37

ӓ

0.37



0.36

…)

0.36

[…]

0.36

лло

0.35

 चक्रवृद्धि

0.35

POSITIVE LOGITS

 tional

0.75

 tion

0.75

 tions

0.71

 ments

0.68

ing

0.63

 sion

0.62

 tive

0.61

 ción

0.59

-_

0.54

-.

0.52

Activations Density 0.041%