INDEX

Explanations

numbers and statistics

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

panjang

-1.16

 advantageous

-1.15

 Đông

-1.13

 kveld

-1.05

 besø

-1.05

But

-1.02

Kön

-1.02

ēju

-1.02

Why

-1.00

 jogar

-1.00

POSITIVE LOGITS

often

1.32

 sempre

1.18

 FUCKING

1.14

including

1.10

ating

1.10

 nuovo

1.09

usually

1.08

still

1.07

IA

1.05

 asla

1.04

Activations Density 0.088%