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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of updating or being kept up to date

    oai_token-act-pair · gpt-3.5-turbo

    instances of updates or changes in information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aden
    -0.85
    á
    -0.77
    ang
    -0.76
    bors
    -0.75
    avery
    -0.74
     Berm
    -0.71
    bara
    -0.69
    bia
    -0.67
    alty
    -0.67
    acht
    -0.67
    POSITIVE LOGITS
     snapshots
    0.86
     update
    0.86
     updates
    0.82
     notifications
    0.82
     versions
    0.78
     refresh
    0.77
     snapshot
    0.77
    Attempts
    0.75
     updating
    0.74
     timestamp
    0.73
    Act Density 0.016%

    No Known Activations