INDEX

Explanations

The neuron strongly activates on single-word English prepositions (like “in,” “on,” “at,” “under”) indicating location or context.

prepositions followed by location or context

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

to

-1.72

-1.62

</td>

-1.42

You

-1.41

by

-1.38

而

-1.32

this

-1.26

</em>

-1.26

বা

-1.23

POSITIVE LOGITS

</h1>

1.61

ねば

1.43

rabh

1.41

</strong>

1.39

 trayectoria

1.29

hermoso

1.29

 maximizes

1.27

姿

1.26

💟

1.23

Activations Density 0.082%