INDEX

Explanations

programming variables and parameters

The neuron consistently spikes on occurrences of the single-letter identifier “p” (i.e. a variable or function parameter named p) in code.

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

-1.98

and

-1.65

 vielleicht

-1.55

 describir

-1.49

竺

-1.47

 zuerst

-1.42

 ブック

-1.41

</sup>

-1.41

or

-1.39

 появля

-1.38

POSITIVE LOGITS

樒

2.09

⤞

1.84

されない

1.83

籥

1.79

 esferas

1.74

BITDA

1.73

葑

1.68

垕

1.68

ﮦ

1.67

 diğer

1.65

Activations Density 0.019%