INDEX

Explanations

Web encoding and programming constructs

This neuron detects programming tokens for escaping or encoding text (e.g. HTML escaping and URL‐encoding functions).

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

</b>

-1.57

 exclusivo

-1.53

ȧ

-1.52

The

-1.48

 atendido

-1.45

句话

-1.37

 entendido

-1.37

鴞

-1.35

</h5>

-1.35

 subjected

-1.34

POSITIVE LOGITS

2.08

2.00

1.98

while

1.73

1.66

 نداشته

1.65

1.63

睒

1.60

1.57

Surely

1.53

Activations Density 0.003%