INDEX

Explanations

designed around

The neuron specifically detects the word “around,” especially when used to indicate an approximate quantity or value.

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

 they

-2.02

-1.75

in

-1.56

一辈子

-1.53

 still

-1.52

消失了

-1.50

all

-1.44

 list

-1.41

人是

-1.41

ⓣ

-1.40

POSITIVE LOGITS

啣

1.82

튿

1.78

쨩

1.77

ޞ

1.76

 faldas

1.73

 Eigentümer

1.69

ዣ

1.67

 taşlı

1.66

alumnos

1.63

瑆

1.61

Activations Density 0.008%