INDEX

Explanations

locations connected by prepositions or vs

This neuron strongly activates on short relational function words—especially prepositions like “with,” “to,” “vs,” “from,” and “of.”

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

and

-2.03

),

-1.92

なども

-1.62

);

-1.56

に行ってきました

-1.49

);

-1.48

see

-1.38

get

-1.38

」、

-1.37

POSITIVE LOGITS

bisa

1.52

 stratég

1.46

 secretos

1.45

dailymail

1.44

िये

1.42

 cráneo

1.41

Spire

1.41

嵛

1.38

 gewährleisten

1.37

 Houſe

1.36

Activations Density 0.061%