INDEX

Explanations

at the moment or lately

The neuron fires on temporal adverbs or expressions denoting current or recent time (e.g. “now,” “moment,” “days,” “lately”).

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

 there

-1.73

 this

-1.73

 with

-1.59

忖

-1.54

𖥧

-1.49

欵

-1.49

 potencial

-1.48

of

-1.47

 Terkait

-1.46

 Berikut

-1.45

POSITIVE LOGITS

1.91

1.71

1.59

 mensuales

1.55

 опас

1.50

1.49

就

1.46

–

1.45

Activations Density 0.096%