INDEX

Explanations

motivations and intentions

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

the

-1.86

 acogedor

-1.57

 encantador

-1.52

лович

-1.46

mittag

-1.46

 filósofo

-1.44

―――

-1.42

 jabón

-1.41

nappropriate

-1.37

photobucket

-1.37

POSITIVE LOGITS

 motives

1.97

oughed

1.45

↵

1.45

1.41

migrationBuilder

1.38

ቍ

1.36

1.34

すすめ

1.33

之所

1.32

Activations Density 0.030%