INDEX

Explanations

forms of 'to be' or 'to have'

The neuron fires on personal‐address constructions—especially first‐ and second‐person pronouns (“I,” “you”) plus forms of the verb “to be” (am/are/’s, including negations like “wasn’t”).

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

 also

-1.62

ก็

-1.44

也是

-1.43

Quoi

-1.41

גם

-1.41

}$

-1.39

بغ

-1.39

Même

-1.38

();

-1.35

５

-1.35

POSITIVE LOGITS

 there

1.45

である

1.36

穣

1.34

 alcune

1.30

如此

1.28

 today

1.27

 mainten

1.27

 alcuni

1.23

 بتوان

1.22

 being

1.21

Activations Density 0.025%