INDEX

Explanations

case object and Q: questions

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

-1.73

')

-1.63

</u>

-1.61

 alebo

-1.59

it

-1.55

-1.54

 spørs

-1.54

 eerste

-1.52

enschappelijke

-1.52

POSITIVE LOGITS

</h2>

2.17

Of

1.78

1.73

在這

1.58

鹟

1.57

They

1.52

𝓃

1.49

 also

1.48

</td>

1.47

After

1.45

Activations Density 0.000%