INDEX

Explanations

$x^2$ and $y^2$ expressions

This neuron activates on numeric tokens (e.g. integers or decimals) in mathematical expressions—that is, it detects literal numbers.

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

or

-1.72

ramientas

-1.66

紧急

-1.58

aterin

-1.56

阴影

-1.48

-1.46

 региона

-1.45

 Ortschaft

-1.41

ників

-1.41

phée

-1.40

POSITIVE LOGITS

-------

2.02

 conquistar

1.77

--

1.75

THEY

1.65

 немає

1.62

----------

1.61

There

1.60

If

1.59

جوا

1.59

 betreft

1.59

Activations Density 0.033%