INDEX

Explanations

marshalling bytes or buffers

The neuron fires on code tokens referring to raw binary data—especially “byte”/“bytes” types, byte-array literals (b'…'), and related buffer operations.

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

even

-1.60

-1.46

who

-1.33

-1.30

what

-1.30

lıkla

-1.27

while

-1.27

selben

-1.26

if

-1.25

POSITIVE LOGITS

 Cuando

1.47

<bos>

1.41

ámica

1.35

TacToe

1.30

ficulties

1.27

||

1.23

niť

1.23

to

1.22

vedades

1.20

metology

1.20

Activations Density 0.037%