INDEX

Explanations

shapes and points

The neuron detects descriptive terms referring to shape or form (e.g. “rounded,” “pointed,” “arched,” “obtuse,” “pupiform,” etc.).

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

romeda

-1.41

uating

-1.39

quing

-1.38

 grasas

-1.36



-1.34

 employé

-1.31

 creativos

-1.30

WARDS

-1.28

 vektör

-1.28

ној

-1.27

POSITIVE LOGITS

1.31

It

1.16

1.15

of

1.13

We

1.13

 each

1.13

1.08

at

1.07

<b>

1.05

Activations Density 0.098%