INDEX

Explanations

indoor, highest, Hop, recent, most, hits, single

The neuron strongly activates on numeric tokens—quantities, measurements, years, percentages, and other numbers.

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

 svých

-1.41

dö

-1.29

 there

-1.25

Тран

-1.21

or

-1.17

Objekt

-1.16

 jiné

-1.14

޸

-1.11

 anunciado

-1.09

ப்பு

-1.09

POSITIVE LOGITS

1.28

."));

1.26

 that

1.19

who

1.17

grads

1.13

jenige

1.11

 désormais

1.08

still

1.08

 vẫn

1.07

 violência

1.06

Activations Density 0.247%