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

    Neuronpedia

    INDEX
    Explanations

    editor's notes within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to editorial notes or comments within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metics
    -0.71
    unin
    -0.64
     Macedonia
    -0.62
    milo
    -0.62
    omething
    -0.61
     vain
    -0.61
    enegger
    -0.60
     uphill
    -0.59
    adra
    -0.58
     Sicily
    -0.57
    POSITIVE LOGITS
    ial
    1.11
    ially
    0.94
     Comments
    0.92
     Rating
    0.88
     Picks
    0.88
     Note
    0.85
     Message
    0.84
    Reviewed
    0.82
    ials
    0.81
     Notes
    0.78
    Act Density 0.053%

    No Known Activations