INDEX

Explanations

mathematical equations or problems

The neuron consistently lights up on individual numeric tokens (i.e. standalone digits).

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

 compartió

-1.92

 vivió

-1.83

 siguió

-1.81

 logró

-1.78

 past

-1.70

 consiguió

-1.69

 помогают

-1.67



-1.66

 nouvel

-1.63

 tomó

-1.60

POSITIVE LOGITS

或者

2.03

Вариан

1.95

çou

1.95

อีก

1.94

灃

1.92

 wayward

1.91

螓

1.88



1.86

໊

1.84

蒗

1.84

Activations Density 0.053%