INDEX

Explanations

css units (rem, em, px)

The neuron fires on numeric constants in code, such as standalone integers or decimal values (e.g. “2”, “19.75”, “84”, “191”).

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

 that

-2.30

 could

-2.16

 would

-1.91

 might

-1.84

 will

-1.84

 also

-1.84

can

-1.83

It

-1.81

of

-1.70

on

-1.70

POSITIVE LOGITS

顴

1.92

鱨

1.82

蛲

1.80

 guapos

1.78

కర్య

1.77

ſche

1.77

໑

1.76

 probabilidad

1.70

耵

1.70

 anoche

1.64

Activations Density 0.044%