INDEX

Explanations

punctuation followed by a word

The neuron fires on literal constants—numbers or quoted string values appearing in the code.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

in

-1.48

個室

-1.20

饗

-1.19

to

-1.17

儀式

-1.16

but

-1.15

-1.13

 amidst

-1.11

 odpově

-1.09

させていただきました

-1.08

POSITIVE LOGITS

 qualsiasi

1.39

為に

1.30

ㅛ

1.30

 cualquiera

1.27

,.

1.27

 .........

1.24

ところです

1.20

 .............

1.20

','

1.17

 betere

1.15

Activations Density 0.055%