INDEX

Explanations

defeating followed by names

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

Mr

-1.43

Mr

-1.30

 آقای

-1.29

 disponibilités

-1.27

我们

-1.24

ſſi

-1.21

 naszych

-1.16

我们的

-1.16

 MINUTES

-1.15

 nossa

-1.14

POSITIVE LOGITS

 other

1.57

 both

1.48

 another

1.34

 only

1.30

1.18

 fellow

1.14

 some

1.13

new

1.10

 many

1.10

 every

1.09

Activations Density 0.083%