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

    Neuronpedia

    INDEX
    Explanations

    people's names, specifically the name "Andrea"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Andrea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.96
    Ħ¢
    -0.88
    mares
    -0.88
    lining
    -0.86
    ghai
    -0.84
    emouth
    -0.83
    onew
    -0.81
    azer
    -0.80
    INESS
    -0.80
    osuke
    -0.79
    POSITIVE LOGITS
     Rossi
    1.07
     Tant
    0.77
     Ces
    0.77
     Grimes
    0.76
    ption
    0.74
     Devi
    0.74
    ptions
    0.73
    zzo
    0.72
     Michele
    0.67
     Netanyahu
    0.66
    Act Density 0.074%

    No Known Activations