INDEX

Explanations

any or all conditions

The neuron fires on tokens that mark existence or membership checks in code (e.g. “Where”, “Any”, “Contains”).

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

 gdyż

-0.93

arian

-0.85

箐

-0.84

gląd

-0.82

 nonché

-0.80

дневно

-0.79

_$

-0.77

tehende

-0.77

waukee

-0.75

$/,

-0.75

POSITIVE LOGITS

any

3.81

any

2.81

all

2.63

ANY

2.48

Any

2.42

任何

2.23

ANY

2.16

Any

2.14

 alguno

2.03

 alguna

1.95

Activations Density 0.018%