INDEX

Explanations

full service and range

The neuron fires on numerical quantity tokens—especially decimal or measurement figures in the text.

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

 llegamos

-1.54

 perdió

-1.41

-1.38

-1.33

 parecía

-1.31

 debió

-1.31

 quedaba

-1.27

 apareció

-1.27

 entró

-1.25

 cambió

-1.25

POSITIVE LOGITS

</em>

1.89

ፁ

1.51

 dificil

1.49

of

1.48

袿

1.47

 magasiner

1.46

鍩

1.45

未完

1.43

 including

1.40

utate

1.40

Activations Density 0.039%