INDEX

Explanations

numbers and punctuation

This neuron detects standalone numeric tokens (e.g. volume, issue, page, year, DOI numbers) in citation or reference text.

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

 which

-1.79

of

-1.56

 should

-1.28

 while

-1.27

 would

-1.25

 from

-1.25

 could

-1.24

 these

-1.20

 when

-1.19

 until

-1.19

POSITIVE LOGITS

Seni

1.38

Evet

1.38

Doktor

1.37

Gön

1.34

Teknik

1.34

Aç

1.28

zdroj

1.28

Karakter

1.27

Cevap

1.27

Ilustra

1.25

Activations Density 0.001%