INDEX

Explanations

first instance or time

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dawn

-0.09

stell

-0.08

 diagonal

-0.08

 finals

-0.08

amber

-0.08

endor

-0.08

GLOBALS

-0.08

ceb

-0.08

emer

-0.07

ilan

-0.07

POSITIVE LOGITS

few

0.33

few

0.25

Few

0.22

Few

0.21

 several

0.20

 dozen

0.17

 couple

0.17

 Several

0.15

 handful

0.15

 quelques

0.14

Activations Density 0.194%