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

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.94
     conflic
    -0.82
     pregn
    -0.75
     citiz
    -0.75
     subscript
    -0.74
     unden
    -0.72
     disparate
    -0.68
     pestic
    -0.64
    ntil
    -0.64
     swollen
    -0.64
    POSITIVE LOGITS
    ville
    0.97
    hurst
    0.90
     Jr
    0.89
     County
    0.82
    berger
    0.82
    dale
    0.81
    ridge
    0.81
    berg
    0.80
    wood
    0.80
    burgh
    0.80
    Act Density 0.451%

    No Known Activations