INDEX

Explanations

opening quotes and special characters

The neuron fires strongly on single-character literals of punctuation or operator symbols (e.g. “:”, “\\”, “+”, “-”)—i.e. when a document token is a quoted single-character escape/operator symbol.

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

of

-3.16

</h3>

-2.70

⚌

-2.69

苤

-2.67

</em>

-2.59

 beberapa

-2.58

 cadeira

-2.45

觏

-2.45

퐸

-2.42

敺

-2.41

POSITIVE LOGITS

there

3.16

From

2.89

when

2.80

With

2.78

!!!!!

2.75

This

2.52

!!!!

2.52

⤵

2.48

with

2.44

！！”

2.39

Activations Density 0.005%