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

    Neuronpedia

    INDEX
    Explanations

    names of organizations and geographic locations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.66
     surla
    -0.66
    艋
    -0.63
     Metropolitan
    -0.59
    GOTREF
    -0.59
    oquia
    -0.59
     Erzb
    -0.59
    #+#
    -0.57
    MLLoader
    -0.57
    UnsafeEnabled
    -0.56
    POSITIVE LOGITS
     rurales
    0.65
    şağı
    0.60
     villagers
    0.55
     Navajo
    0.55
    tuan
    0.54
    gany
    0.52
    HomeAsUpEnabled
    0.52
     villager
    0.51
     Kettle
    0.51
    万美元
    0.50
    Act Density 0.069%

    No Known Activations