INDEX

Explanations

phone number or calls

The neuron specifically detects occurrences of the word “phone” (i.e. mentions of a telephone).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

menjadi

-1.91

which

-1.80

苼

-1.69

在其

-1.67

Dữ

-1.66

imagens

-1.63

-1.62

bảng

-1.59



-1.57

 ambayo

-1.56

POSITIVE LOGITS

月末

1.87

輅

1.69

 number

1.59

one

1.57

ון

1.56

 mereka

1.55

 phone

1.54

two

1.53

 call

1.52

 customer

1.52

Activations Density 0.032%