INDEX

Explanations

know to, know that, time that, see anything

The neuron fires most strongly on words of knowing, thinking, or perceiving (e.g. know, see, show, brain, thing).

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

 there

-1.88

 first

-1.63

there

-1.52

at

-1.50

There

-1.45

 every

-1.44

-1.42

new

-1.38

 then

-1.37

 making

-1.36

POSITIVE LOGITS

htë

1.39

 disebabkan

1.34

 článek

1.32

kém

1.30

 TMPro

1.27

 portanto

1.26

MMMM

1.25

dreamstime

1.25

nachweise

1.25

っている

1.25

Activations Density 0.147%