INDEX

Explanations

initials and punctuation

This neuron detects numeric tokens, especially numbers with decimal points (e.g. “114.5,” “105.5,” “95.5”).

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

lético

-1.72

涐

-1.67

槼

-1.67

 churrasco

-1.62

 ajuta

-1.61

 galinha

-1.59

 bekan

-1.59

过来了

-1.57

 connaît

-1.56

实话

-1.53

POSITIVE LOGITS

or

1.55

to

1.45

’

1.41

 tillegg

1.38

 После

1.33

 некоторые

1.32

、

1.31

 主要

1.29

 основ

1.26

</h4>

1.20

Activations Density 0.037%