INDEX

Explanations

except followed by contrasting information

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

However

-1.98

 แต่

-1.55

趼

-1.49

𞤢

-1.48

了一個

-1.44

.);

-1.41

);

-1.38

</b>

-1.38

葡萄酒

-1.38

 deixar

-1.36

POSITIVE LOGITS

we

1.83

歺

1.79

 they

1.64

</h3>

1.57

htë

1.51

ïlande

1.49

ází

1.46

或者

1.45

的技术

1.45

复制代码

1.43

Activations Density 0.012%