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

    Neuronpedia

    INDEX
    Explanations

    mentions of names, specifically the name "Julie" and "Buckley"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the names "Julie" and "Buckley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aries
    -0.97
    ific
    -0.95
    icum
    -0.92
    iger
    -0.91
    ices
    -0.91
    ario
    -0.91
    icans
    -0.89
    ago
    -0.89
    hof
    -0.88
    idad
    -0.87
    POSITIVE LOGITS
     Steele
    0.76
     disadvant
    0.76
     dossier
    0.75
     juicy
    0.72
    volent
    0.69
    racuse
    0.62
     stren
    0.62
     barg
    0.60
    çĶŁ
    0.60
     cozy
    0.58
    Act Density 0.062%

    No Known Activations