INDEX

Explanations

years ago

The neuron strongly fires on numeric tokens representing years or time spans (e.g. floating-point “years” values).

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

رل

0.69

 poblaciones

0.66

拃

0.63

hattam

0.62

 Planet

0.60

κολ

0.60

 लगातार

0.59

ческим

0.59

 Familien

0.59

ustrated

0.59

POSITIVE LOGITS

소

0.77

ago

0.74

ما

0.66

 geleden

0.64

说

0.64

แต่ง

0.62

дів

0.62

ва

0.61

อิ

0.60

 antise

0.60

Activations Density 0.036%