INDEX

Explanations

tend to

The neuron detects occurrences of the verb “tend” (in forms like “tends to” or “tend to”) indicating a tendency.

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

ViewChild

-1.75



-1.70

randrange

-1.69

Includes

-1.64

𖤍

-1.62

糌

-1.59

 about

-1.59

OUTUBE

-1.59

 laranja

-1.53

 borboleta

-1.52

POSITIVE LOGITS

</sup>

2.47

);

1.64

</h2>

1.56

1.51

他の

1.40

 завжди

1.38

 explanations

1.31

 Saltar

1.31

{~

1.29

Activations Density 0.012%