INDEX

Explanations

collision and intersection detection

The neuron fires on mentions of collisions (e.g. “collision,” “colliding,” “collide”) in technical or code contexts.

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

</h3>

-1.84

-1.52

$}

-1.49

</h5>

-1.48

);

-1.45

henswürdigkeiten

-1.45

 same

-1.45

 появились

-1.45

 nación

-1.45

</u>

-1.38

POSITIVE LOGITS

<bos>

1.70

 ruso

1.41

 with

1.38

 comigo

1.38

おわりに

1.34

(?)

1.34

 dinosaurio

1.33

1.32

our

1.31

gerakan

1.30

Activations Density 0.009%