INDEX

Explanations

list item separators

colon-like punctuation and symbols

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

했지만

0.55

でしたが

0.50

但我

0.49

<unused2164>

0.45

прочем

0.44

<unused420>

0.44

다라고

0.43

기가

0.43

<unused2121>

0.43

 אבל

0.41

POSITIVE LOGITS

：

1.58

1.57

*:

1.27

1.20

：

1.16

$:

1.15

1.13

):

1.12

`:

1.11

+:

1.10

Activations Density 0.191%