INDEX

Explanations

quotation marks and delimiters

The neuron detects numeric literals (integer and decimal constants) in 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

ykjav

-1.24

 насос

-1.23

ється

-1.14

 esigenze

-1.13

 citazioni

-1.10

čnost

-1.08

 пнев

-1.06

 патро

-1.06

 esperienze

-1.05

 ricerche

-1.05

POSITIVE LOGITS

“

2.25

2.02

‘

1.66

1.60

«

1.46

 ‘‘

1.27

ሺ

1.27

“

1.21

''

1.19

']='

1.18

Activations Density 0.034%