INDEX

Explanations

AM

The neuron activates on tokens containing the substring “AM,” chiefly marking acronyms for cell adhesion molecules (e.g. ICAM-1, VCAM-1).

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

 dünya

-1.48

-1.32

 ziyaretçi

-1.30

 Have

-1.30

Now

-1.29

And

-1.28

 would

-1.28

 remitted

-1.27

 arşiv

-1.26

 HAVE

-1.24

POSITIVE LOGITS



1.58

 actuelles

1.41

 sposob

1.38

ኧ

1.37

AM

1.35

 commerciales

1.32

you

1.31

 είναι

1.30

 подарок

1.28

нении

1.27

Activations Density 0.016%