INDEX

Explanations

@ symbol followed by identifiers

This neuron activates on tokens that represent parameter or variable placeholders prefixed by “@” (e.g., “@instance”, “@test_array”, “@sql”, “@Html.”, “@Ajax.”).

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

in

-1.62

媜

-1.54

who

-1.26

鬓

-1.23

はこの

-1.23

自体

-1.17

vestimento

-1.16

 Оно

-1.16

 špat

-1.15

 also

-1.13

POSITIVE LOGITS

for

1.38

From

1.35

An

1.30

you

1.27

only

1.25

When

1.24

Maybe

1.23

illä

1.22

For

1.20

is

1.18

Activations Density 0.213%