INDEX

Explanations

set forth

The neuron activates on usages of the word “forth,” as in legal or regulatory phrases like “set forth.”

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

待って

-1.80

辄

-1.72

Febru

-1.69

ೣ

-1.66

躓

-1.64

หรือ

-1.59

说说

-1.58

 diversión

-1.56

 caneca

-1.55

ことができます

-1.54

POSITIVE LOGITS

</em>

2.34

.”

2.25

2.14

这

2.02

1.98

要

1.88

這

1.87

“

1.86

 Understand

1.86

ون

1.86

Activations Density 0.001%