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

    Neuronpedia

    INDEX
    Explanations

    references to offline activities or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to offline activities or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aire
    -0.88
    owitz
    -0.88
    ayn
    -0.86
    uay
    -0.85
    alez
    -0.85
    icles
    -0.85
    atories
    -0.83
    atorial
    -0.80
    azaki
    -0.80
    alid
    -0.79
    POSITIVE LOGITS
     standby
    0.73
    spection
    0.70
     offline
    0.68
     computing
    0.68
     maintenance
    0.66
     curfew
    0.63
     reckoning
    0.61
     hiber
    0.61
    phrine
    0.61
     mode
    0.61
    Act Density 0.010%

    No Known Activations