INDEX

Explanations

talent, artists, and potential

This neuron detects occurrences of the word “talent” (and its morphological variants such as “talented” or “talents”).

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>

-2.05

儈

-1.94

焢

-1.92

谂

-1.84

();*/

-1.79

↵

-1.76

They

-1.75

for

-1.73

onomía

-1.73

řit

-1.71

POSITIVE LOGITS

</b>

2.20

ſſen

2.08

</sup>

2.08

</h2>

2.03

to

1.98

 могут

1.92

1.88

1.85

⚣

1.79

</h4>

1.75

Activations Density 0.008%