INDEX

Explanations

path, split, getResource, cache

The neuron is triggered by capitalized identifier fragments—i.e. the CamelCase or PascalCase subwords (class/method/annotation/config names) 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

瑧

-1.57

-1.48

 különböz

-1.45

$}

-1.42

Accademia

-1.41

fani

-1.41

始める

-1.41

 atencion

-1.39

德里

-1.34

]**

-1.34

POSITIVE LOGITS

are

1.61

<bos>

1.47

 justa

1.29

‘

1.27

 oberen

1.26

 bedeutend

1.23

´

1.22

 volle

1.21

umps

1.20

 sech

1.17

Activations Density 0.010%