INDEX

Explanations

words involving "tap"

The neuron fires on occurrences of the token “tap” (in any casing) in code or markup contexts.

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

—

-3.08



-2.59

并

-2.59

 dergleichen

-2.58

 zusätzliche

-2.55

 neue

-2.53

 spezielle

-2.47

 และ

-2.41

 vollständige

-2.39

 alguns

-2.38

POSITIVE LOGITS

ቺ

2.92

2.91

 είναι

2.77

geſ

2.75

For

2.61

 When

2.56

ِّف

2.53

Unlike

2.48

 поверхности

2.47

訕

2.45

Activations Density 0.005%