INDEX

Explanations

punctuation followed by consequence

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

𒅗

1.51

ịp

1.48

 구성

1.47

𒆪

1.40

세

1.37

ប្រតិ

1.36

댜

1.35

avacak

1.35

 선보

1.34

梘

1.33

POSITIVE LOGITS

 basically

1.82

 obviamente

1.54

Basically

1.53

 whatever

1.52

なんか

1.50

というか

1.48

 Basically

1.46

 maybe

1.46

basically

1.45

 obviously

1.45

Activations Density 0.219%