Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sections in a text that have been edited

    oai_token-act-pair · gpt-3.5-turbo

    sections or headings of structured content, particularly in academic or informational texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.81
     citiz
    -0.80
     ende
    -0.73
    userc
    -0.71
    umbers
    -0.69
     incarcer
    -0.69
    terday
    -0.68
     neighb
    -0.66
     naughty
    -0.66
     choking
    -0.65
    POSITIVE LOGITS
    References
    1.01
    Trivia
    0.93
    âĨij
    0.83
    Associated
    0.80
    Appearances
    0.80
    Gallery
    0.79
    ccording
    0.79
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.78
    >>>>>>>>
    0.76
    Production
    0.75
    Act Density 0.082%

    No Known Activations