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

    Neuronpedia

    INDEX
    Explanations

    instances where an event or action happens multiple times

    oai_token-act-pair · gpt-3.5-turbo

    references to repeated events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.77
    CHAT
    -0.70
    uala
    -0.69
    ebook
    -0.67
    oras
    -0.63
    erest
    -0.61
    erto
    -0.61
    urate
    -0.60
    ordes
    -0.60
    aceous
    -0.60
    POSITIVE LOGITS
    frames
    0.85
    abl
    0.78
    frame
    0.75
    points
    0.69
    姫
    0.68
    é¾įå
    0.66
    period
    0.66
    etheless
    0.65
    cone
    0.65
    asons
    0.64
    Act Density 0.056%

    No Known Activations