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

    Neuronpedia

    INDEX
    Explanations

    references to large-scale objects or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale systems or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idges
    -0.87
    cair
    -0.80
    swick
    -0.74
    rium
    -0.73
    edin
    -0.73
    oother
    -0.72
    phis
    -0.69
    ipedia
    -0.69
    ournal
    -0.69
     Parsons
    -0.69
    POSITIVE LOGITS
     fabrication
    0.84
     deployment
    0.80
     production
    0.80
     fulfillment
    0.79
    enter
    0.76
     ecological
    0.74
     scale
    0.74
     accident
    0.74
     adoption
    0.73
     undertaking
    0.72
    Act Density 0.026%

    No Known Activations