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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, specifically the name "Lee"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Lee."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rontal
    -0.78
    orate
    -0.69
    security
    -0.67
    icted
    -0.64
    unct
    -0.64
    ALLY
    -0.64
    ional
    -0.63
    omething
    -0.63
    ICAN
    -0.63
    ties
    -0.63
    POSITIVE LOGITS
    Anne
    1.04
     Stras
    0.88
     Harvey
    0.87
    utenant
    0.85
    lee
    0.84
    warm
    0.84
    wei
    0.83
    vel
    0.77
    vers
    0.77
    ppa
    0.76
    Act Density 0.020%

    No Known Activations