INDEX

Explanations

first-person shooter games

The neuron is a number detector – it activates on numeric tokens (e.g. “360,” “328,” “13,” etc.), with stronger activations for larger values.

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

彣

-2.75

蕻

-2.47

 bestowed

-2.42

軔

-2.41

 liked

-2.36

omiast

-2.28

凊

-2.27

 ALWAYS

-2.27

-2.23

 осіб

-2.20

POSITIVE LOGITS

2.75

</strong>

2.75

ти

2.39

also

2.34

these

2.33

й

2.33

 várias

2.28

ó

2.27

if

2.22

 wilden

2.20

Activations Density 0.003%