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

    Neuronpedia

    INDEX
    Explanations

    words related to legal proceedings and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to popular media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subdiv
    -0.52
     regist
    -0.52
     taxing
    -0.50
     interven
    -0.50
    ordinate
    -0.50
     manufactures
    -0.50
     busiest
    -0.48
     Panic
    -0.48
     Plate
    -0.48
     incorpor
    -0.47
    POSITIVE LOGITS
    hammad
    0.65
    ée
    0.58
    ument
    0.58
    aughs
    0.57
    anu
    0.56
    tesy
    0.56
    qqa
    0.55
    amation
    0.55
    opathy
    0.54
    acus
    0.52
    Act Density 1.508%

    No Known Activations