INDEX

Explanations

-ism, -ist, and -istic suffixes

The neuron activates on occurrences of academic “-ism” or “-ist” terms—especially theory names like constructivism, constructivist, and interactionism.

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

 lika

-1.41

 cirka

-1.32

 Tahun

-1.31

 preocupado

-1.25

tersebut

-1.25

 éves

-1.24

 yılında

-1.24



-1.22

 syke

-1.22

 Agustus

-1.22

POSITIVE LOGITS

1.48

 musia

1.39

 mojej

1.34

 šed

1.33

 haupts

1.31

 genauer

1.30

決して

1.29

 mogę

1.27

を設定

1.27

挑戦

1.27

Activations Density 0.019%