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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, especially notable figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.77
     capitals
    -0.71
    regulated
    -0.70
     princ
    -0.69
     refinement
    -0.67
     secretaries
    -0.67
     mathemat
    -0.65
    CLASSIFIED
    -0.63
     captcha
    -0.62
    authorized
    -0.62
    POSITIVE LOGITS
     Chapman
    0.83
     Cornel
    0.79
     McL
    0.78
     Sinclair
    0.75
     Mc
    0.75
     Savage
    0.73
     Malone
    0.73
     Cant
    0.72
     McInt
    0.72
     Canaver
    0.72
    Act Density 0.284%

    No Known Activations