INDEX

Explanations

lip colour and cosmetics

The neuron fires on occurrences of the substring “lip” (e.g. “lip,” “lips”) in any context.

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

—

-2.06

-2.03

at

-1.97

温和

-1.84

”

-1.80

ありました

-1.77

アレル

-1.77

 seater

-1.71

 dieß

-1.68

ありますが

-1.67

POSITIVE LOGITS

 ..."

2.31

</h1>

2.22

 parfüm

2.11

2.08

ﹶ

2.05

влений

1.93

?...

1.90

 parfü

1.89



1.83

ارتمان

1.81

Activations Density 0.007%