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

    Neuronpedia

    INDEX
    Explanations

    names likely to refer to a specific person ('Susan')

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Susan" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORD
    -0.76
    iculty
    -0.76
    cffffcc
    -0.72
    unct
    -0.68
     compr
    -0.66
     unpredictable
    -0.64
     paced
    -0.63
    Constructed
    -0.61
    riter
    -0.61
    olkien
    -0.61
    POSITIVE LOGITS
    ne
    1.01
    anne
    0.95
    icide
    0.92
     Rice
    0.90
    otte
    0.89
    gha
    0.85
     Boyle
    0.85
    mary
    0.84
    Anne
    0.83
    jit
    0.82
    Act Density 0.034%

    No Known Activations