INDEX

Explanations

code and section headers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

by

-1.08

 even

-1.07

 which

-1.02

 spurred

-1.01

 providing

-1.00

 because

-1.00

 Providing

-0.98

 through

-0.98

!!!!!

-0.98

 venturing

-0.96

POSITIVE LOGITS

 alcune

1.09

 alcuni

1.07

 secluded

1.04

immediately

1.00

 gewi

1.00

besides

0.98

generally

0.97

 alguns

0.95

usually

0.94

 eenig

0.94

Activations Density 0.001%