INDEX

Explanations

case " " or alternative

The main thing this neuron does is detect numeric tokens (numbers and digit sequences) in the text.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

そして

0.73

которые

0.70

}$;

0.70

 फेब्रुवारी

0.70

 tiap

0.68

และการ

0.68

 आणि

0.67

慢慢

0.67

数列

0.67

再び

0.66

POSITIVE LOGITS

or

1.55

 или

1.47

或

1.40

 یا

1.37

 atau

1.34

 hoặc

1.34

 alebo

1.34

或是

1.34

 veya

1.33

ή

1.32

Activations Density 0.191%