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

    Neuronpedia

    INDEX
    Explanations

    people's names followed by digits, specifically "Brooks" followed by numbers 8 or 9

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Brooks."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izoph
    -0.84
    ministic
    -0.77
    istor
    -0.75
    ality
    -0.75
    ugal
    -0.75
    awei
    -0.73
    igators
    -0.72
    izen
    -0.72
    abetic
    -0.71
    emonic
    -0.70
    POSITIVE LOGITS
     Brothers
    0.93
    oks
    0.91
    dale
    0.91
    boro
    0.90
     Brooks
    0.87
    ville
    0.80
     Reed
    0.80
     Jenner
    0.78
    lee
    0.75
    coe
    0.74
    Act Density 0.023%

    No Known Activations