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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to hometowns and native places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.88
    inventoryQuantity
    -0.80
    ensibly
    -0.77
    xual
    -0.74
    emis
    -0.74
    odiac
    -0.72
    atonin
    -0.70
     Emails
    -0.70
    itual
    -0.69
    ifest
    -0.68
    POSITIVE LOGITS
     Tanzania
    0.87
     Latvia
    0.84
     Ethiopia
    0.80
     Argentina
    0.80
     Bosnia
    0.76
     Judah
    0.76
     Normandy
    0.75
     Tong
    0.75
     Armenia
    0.75
     hometown
    0.75
    Act Density 0.126%

    No Known Activations