INDEX

Explanations

at locations and organizations

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

灃

-1.82

 maleta

-1.70

 его

-1.68

 coloridas

-1.55

いかがでしたか

-1.54

鴒

-1.54

 bonitas

-1.52

⌄

-1.51

 jego

-1.47

スコット

-1.46

POSITIVE LOGITS

of

2.47

1.88

the

1.77

1.66

之事

1.59

 however

1.56

1.51

1.50

to

1.45

 both

1.45

Activations Density 0.077%