INDEX

Explanations

near to

The neuron activates on the preposition “to” when it introduces a numeric measurement (e.g. distances or quantities).

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



-1.84

 affez

-1.83

涐

-1.72

him

-1.71

 ścian

-1.69

 protože

-1.66

Vgl

-1.64

/");

-1.60

 tył

-1.59

 См

-1.55

POSITIVE LOGITS

</strong>

2.09

1.84

–

1.81

1.57

‑

1.56

ities

1.55

",

1.55

and

1.54

dientemente

1.47

és

1.45

Activations Density 0.076%