INDEX

Explanations

when and where needed

The neuron fires on temporal or conditional markers—words and tokens that specify “when,” “where,” “times,” “due,” “arrives,” etc., i.e. timing and scheduling cues.

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

-1.84

to

-1.83

 should

-1.37

 through

-1.26

 over

-1.25

 always

-1.24

 ALWAYS

-1.23

Always

-1.20

 usually

-1.19

 involucra

-1.17

POSITIVE LOGITS

 essas

1.31

因为

1.31

 same

1.31

因為

1.30

 disques

1.29

 adott

1.24

듦

1.23

xref

1.22

 särsk

1.21

 liknande

1.20

Activations Density 0.073%