INDEX

Explanations

:Pages

This neuron detects multi-letter uppercase abbreviations or acronyms.

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

 podľa

-1.60

؟

-1.48

ธ

-1.43

Recuerda

-1.42

Britt

-1.41

 dejan

-1.40

ਲ਼

-1.39

ğu

-1.38

 {}));

-1.38

lllll

-1.37

POSITIVE LOGITS

 including

1.48

 such

1.38

and

1.35

 budapest

1.32

饜

1.30

 pascua

1.27

’

1.25

 than

1.20

 レンタル

1.16

ような

1.15

Activations Density 0.008%