INDEX

Explanations

programming and commands

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

<bos>

-2.06

if

-1.63

 have

-1.61

 when

-1.58

そのため

-1.56

 mientras

-1.55

 cuando

-1.53

しかし

-1.50

これは

-1.50

它的

-1.46

POSITIVE LOGITS

the

1.85

 into

1.72

了

1.70

おわりに

1.69

ほら

1.62

えっ

1.61



1.52

 tirantes

1.51

㩒

1.51

明日は

1.48

Activations Density 0.001%