INDEX

Explanations

from followed by an entity

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

</em>

-2.31

fying

-1.74

橚

-1.62

plained

-1.53

stacles

-1.51

</sup>

-1.48

髎

-1.48

ociação

-1.46

ctible

-1.45

salms

-1.45

POSITIVE LOGITS

1.59

1.55

之际

1.55

1.48

相對

1.45

謌

1.45

{};

1.44

 pembun

1.42

可能会

1.38

陆续

1.37

Activations Density 0.052%