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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimed
    -0.77
    kson
    -0.73
    peror
    -0.71
    uthor
    -0.69
    visor
    -0.69
    zai
    -0.68
    ERAL
    -0.67
    ced
    -0.66
     Viking
    -0.66
    olkien
    -0.65
    POSITIVE LOGITS
     McCull
    1.08
     McCorm
    0.86
     pige
    0.81
     mills
    0.75
    sburg
    0.75
    inx
    0.74
    matter
    0.72
     crates
    0.72
     McCabe
    0.71
    arty
    0.69
    Act Density 0.015%

    No Known Activations