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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly focusing on the name "Sophie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sophie" and related proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.86
    ees
    -0.83
    inez
    -0.81
    iggurat
    -0.78
    itated
    -0.76
    ports
    -0.75
    redo
    -0.73
    herty
    -0.73
    orne
    -0.72
    ulhu
    -0.72
    POSITIVE LOGITS
     Sophie
    0.84
     Choice
    0.80
    oleon
    0.79
    isters
    0.73
    atis
    0.72
     Vie
    0.69
    ISM
    0.68
     Breaker
    0.68
     Gö
    0.67
     Sasha
    0.67
    Act Density 0.022%

    No Known Activations