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

    Neuronpedia

    INDEX
    Explanations

    instances where a specific event or action has occurred multiple times

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of times an event has occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dinand
    -0.72
     Skydragon
    -0.70
    BILITIES
    -0.67
    odox
    -0.65
    isson
    -0.65
    Versions
    -0.61
    CSS
    -0.61
    ItemTracker
    -0.60
    ription
    -0.56
    Rap
    -0.56
    POSITIVE LOGITS
    secut
    0.78
     consecutive
    0.77
     strugg
    0.67
    imester
    0.66
    pires
    0.66
    aneers
    0.65
    wcs
    0.64
     embattled
    0.63
     approvals
    0.62
     anniversary
    0.61
    Act Density 0.210%

    No Known Activations