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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically focusing on the name "Derek"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Derek."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.82
    izations
    -0.80
    ILA
    -0.80
     actionGroup
    -0.80
    inventoryQuantity
    -0.72
    shapeshifter
    -0.71
    CHO
    -0.71
    places
    -0.69
    inters
    -0.69
    EMS
    -0.68
    POSITIVE LOGITS
     Derek
    0.79
    resy
    0.76
     Owen
    0.75
     Carr
    0.71
     Lawson
    0.71
     Jar
    0.70
     Crosby
    0.70
    bard
    0.69
     Cage
    0.69
     Alexander
    0.69
    Act Density 0.006%

    No Known Activations