INDEX

Explanations

made of materials

The neuron activates on mentions of physical materials or substances (e.g., wood, metal, cardboard, ceramic, resin).

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

in

-2.50

for

-1.30

on

-1.26

his

-1.20

 الوزراء

-1.16

-1.15

as

-1.14

bujete

-1.13

if

-1.12

at

-1.08

POSITIVE LOGITS

 énorm

1.54

 jotka

1.48

 engend

1.45

 laiss

1.44

 sembl

1.44

 réve

1.42

illigen

1.40

 Эти

1.38

 indisponible

1.37

 Rumuni

1.34

Activations Density 0.052%