INDEX

Explanations

link rel="stylesheet" imgs/https server .css

The neuron fires on numeric tokens (sequences of digits) in the HTML/XML markup.

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

 doesn

-1.98

 didn

-1.92

 wasn

-1.91

did

-1.91

，「

-1.88

has

-1.88

！（

-1.87

 does

-1.86

というわけで

-1.85

呖

-1.83

POSITIVE LOGITS

栳

2.58

馓

2.33

蛲

2.27

 sechs

2.23

各样的

2.17

鲞

2.13

為に

2.11

 ซึ่ง

2.11

 zufried

2.02

 zwanzig

2.02

Activations Density 0.001%