INDEX

Explanations

states and functions

The neuron detects quantitative numeric tokens and references—numbers in parentheses or brackets (e.g. citation indices, years, doses), decimal values, and other numeric expressions.

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

 dovrebbe

-1.30

 wichtigste

-1.27

 dikel

-1.27

 cardiovas

-1.25

Dimensioni

-1.21

astify

-1.21

OBJET

-1.20

 palio

-1.16

を読んで

-1.15

ộp

-1.14

POSITIVE LOGITS

and

1.73

1.61

mpagne

1.58

xvii

1.48

eynman

1.38

1.34

 dejando

1.30

 únicamente

1.30

leveland

1.30

Activations Density 0.116%