INDEX

Explanations

function constructor parameter

The neuron strongly activates on numeric tokens (digits or numbers) in code snippets.

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

panes

-1.16

its

-1.09

 голове

-1.03

yttää

-0.98

ियाँ

-0.93

piles

-0.93

 ihrem

-0.88

телей

-0.87

 venons

-0.86

 recette

-0.85

POSITIVE LOGITS

αι

0.94

못

0.89

WICH

0.85

ΑΙ

0.84

 نیاز

0.84

 heterogeneous

0.83

 bantuan

0.82

glą

0.82

時から

0.81

 perplexed

0.81

Activations Density 0.001%