INDEX

Explanations

programming constructs after punctuation

The neuron activates on identifiers in import/include or namespace/package declarations (e.g. library or framework names in dotted paths).

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

()/

-1.11

 apesar

-1.07

dalla

-1.00

€“

-1.00

joven

-0.99

tissue

-0.99

beqa

-0.98

 deixa

-0.96

ambig

-0.96

iging

-0.96

POSITIVE LOGITS

这个世界

1.00

ografija

0.98

 redeeming

0.90

图形

0.89

參見

0.87

 Yugoslavia

0.87

 ГУ

0.87

蹺

0.86

 discontent

0.84

lète

0.82

Activations Density 0.010%