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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and institutions in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     msec
    -0.75
    brance
    -0.72
     pumps
    -0.71
    BLIC
    -0.70
     Satanic
    -0.69
    Scotland
    -0.69
     livest
    -0.68
     cows
    -0.67
     Odyssey
    -0.62
     miscarriage
    -0.61
    POSITIVE LOGITS
    wei
    1.43
     Xue
    1.30
    jing
    1.28
     Yi
    1.26
     Jiang
    1.26
     Yuan
    1.26
    ui
    1.23
    Hong
    1.22
    zhen
    1.21
     Qing
    1.21
    Act Density 0.184%

    No Known Activations