INDEX

Explanations

like followed by examples

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

на

-1.88

of

-1.73

во

-1.72

 also

-1.65

<>());

-1.63

"--

-1.61

"$

-1.61

-"

-1.58

ка

-1.57

"";

-1.57

POSITIVE LOGITS

Again

1.88

 häufigsten

1.86

:”

1.73

写真を

1.70

 Nachbarn

1.69

 souver

1.66

 являются

1.63

還能

1.60

 zugel

1.57

 Coloque

1.57

Activations Density 0.077%