INDEX

Explanations

The neuron lights up on technical product names, model numbers, sizes, and material/component specifications in construction or industrial contexts.

foundation connecting walls

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

 ativar

-1.67

 balení

-1.65

Ayrıca

-1.58

TIPOS

-1.56

萦

-1.52

 INFORMACIÓN

-1.52

ಝ

-1.51

 дают

-1.50

 lesiones

-1.50

 treino

-1.48

POSITIVE LOGITS

 then

1.59

 with

1.41

if

1.40

 државе

1.38

 before

1.24

 zostanie

1.24

 насеља

1.23

 under

1.20

 Selv

1.19

 проект

1.18

Activations Density 0.063%