INDEX

Explanations

data processing callbacks

The neuron detects numeric literals (tokens containing digits) in code snippets.

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

to

-2.22

-1.65

for

-1.49

：

-1.24

他就

-1.20

صابة

-1.18

他們的

-1.16

but

-1.14

dyti

-1.13

となる

-1.13

POSITIVE LOGITS

 that

2.45

</strong>

1.57

 الرابع

1.45

 aldea

1.44

gantung

1.44

ícias

1.41

attamento

1.41

vého

1.41

vaná

1.40

 henceforth

1.39

Activations Density 0.019%