INDEX

Explanations

mathematical equations and natural language

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

 that

-1.28

-1.23

 lakini

-1.17

ために

-1.16

muslim

-1.12

nke

-1.11

<td>

-1.11

())));

-1.10

ọ

-1.09

POSITIVE LOGITS

Those

1.67

These

1.55

 These

1.40

するもの

1.38

Another

1.37

 Those

1.36

 Seem

1.33

しますね

1.31

ed

1.30

min

1.30

Activations Density 0.005%