INDEX

Explanations

more of a

The neuron activates on numeric tokens (numbers and digit sequences) in the text.

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

ſſen

-2.09

泐

-1.98

还不错

-1.88

嬌

-1.87

很赞

-1.84

the

-1.84

 Ausführungen

-1.80

ll

-1.79

჻

-1.72

to

-1.70

POSITIVE LOGITS

2.73

2.03

</h1>

1.87

)",

1.84

的新

1.81

 pysty

1.75

 églises

1.66

儅

1.66

"]);

1.65

 BoxDecoration

1.64

Activations Density 0.008%