INDEX

Explanations

represents concepts

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mpl

1.13

hill

1.08

elle

1.04

itch

1.03

cham

1.01

atham

1.00

dex

0.99

odge

0.98

oudre

0.96

od

0.95

POSITIVE LOGITS

 LongNumber

1.12

 велоси

1.04

 součást

1.03

 godinu

1.03

 recursively

1.01

סת

0.99

 YEARS

0.99

 абстра

0.98

 satisfactorily

0.98

 contento

0.97

Activations Density 0.272%