INDEX

Explanations

common interjections and phrases

The neuron is detecting proper names (capitalized personal names) in running 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

</h3>

-3.17

ୌ

-2.97

媗

-2.89

na

-2.77

玙

-2.70

𓄹

-2.56

嫆

-2.55

that

-2.53

 letz

-2.52

POSITIVE LOGITS

</b>

2.50

一個

2.47

 consegui

2.39

 struck

2.33

 defied

2.16

美丽的

2.14

 admon

2.11

 quién

2.08

 своей

2.05

很赞

2.05

Activations Density 0.003%