INDEX

Explanations

latex commands and formatting

The neuron strongly activates on numeric tokens (counts, measurements, dates, or statistical figures).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

}[

0.79

}.\

0.75

}{*}{

0.72

}{

0.72

}\

0.70

.}~\

0.67

}.

0.64

},\\

0.63

}\{\

0.62

}\{

0.62

POSITIVE LOGITS

getTo

0.77

――

0.63

バシー

0.61

憧

0.61

imha

0.60

ició

0.60

찮

0.59

ikki

0.58

audioType

0.58

getHours

0.58

Activations Density 0.000%