INDEX

Explanations

rails, railings, and structural elements

The neuron activates on mentions of rail or railing components (e.g., banister, guard rail, stair rail).

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

–

-1.57

 искрен

-1.55

本日の

-1.40

 allmäh

-1.39

Поздрав

-1.30

他的

-1.30

 Insulation

-1.29

-1.28

它的

-1.27

לחה

-1.27

POSITIVE LOGITS

[]:

1.63

ulación

1.53

1.44

?’

1.41

ácie

1.40

’)

1.39

耵

1.38

ны

1.37

ra

1.36

 supuestamente

1.36

Activations Density 0.019%