INDEX

Explanations

names ending with -y or -ty

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

gamesh

-0.73

YR

-0.73

 vantaggi

-0.73

aughn

-0.72

 Verona

-0.72

loid

-0.71

bisch

-0.71

 movimenti

-0.71

frances

-0.71

mazon

-0.71

POSITIVE LOGITS

ody

1.31

gridy

1.14

netty

1.13

ury

1.13

antry

1.09

tidy

1.09

pity

1.09

entity

1.09

ODY

1.07

ety

1.05

Activations Density 0.099%