INDEX

Explanations

technical keywords in code

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

seguir

-1.41

sigue

-1.37

なども

-1.35

薆

-1.34

nuestro

-1.27

física

-1.23

 cinto

-1.22

momento

-1.22

 asiática

-1.18

 tristes

-1.17

POSITIVE LOGITS

1.27

1.18

1.16

擇

1.16

 achieve

1.08

my

1.06

érant

1.05

 configurações

1.03

 kerajaan

1.02

 државе

1.02

Activations Density 0.001%