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

    Neuronpedia

    INDEX
    Explanations

    words related to power or data interruptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to interruptions in service, specifically involving blackouts and outages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.74
    uay
    -0.72
    ilyn
    -0.66
    oph
    -0.65
    ographs
    -0.65
    rib
    -0.64
    itably
    -0.64
    ophile
    -0.64
    tre
    -0.63
    ete
    -0.63
    POSITIVE LOGITS
     shortened
    0.81
     postponed
    0.79
     timetable
    0.75
     lockdown
    0.71
     outage
    0.70
     schedule
    0.70
     plag
    0.69
     downtime
    0.69
    =-=-
    0.68
     blockers
    0.68
    Act Density 0.041%

    No Known Activations