INDEX

Explanations

Generated by

The neuron fires on isolated capitalized names or labels (proper‐noun tokens like “Google,” “Unknown,” “Bluetooth,” “Author,” or “Generated”).

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

 ciudades

-1.01

 ralla

-1.00

ęcia

-0.96

鯵

-0.94

 Armee

-0.94

its

-0.93

aterin

-0.90

ricas

-0.90

遇到的

-0.89

 Zerst

-0.88

POSITIVE LOGITS

</i>

1.21

+:+

1.06

</

1.05

</b>

1.00

ELSE

0.91

 while

0.90

 after

0.87

<td>

0.86

找

0.85

</td>

0.85

Activations Density 0.001%