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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Emily

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ername
    -0.77
    tenance
    -0.75
    emonium
    -0.73
    lasses
    -0.70
    nown
    -0.70
    nings
    -0.70
    ebin
    -0.69
    nesses
    -0.69
    animous
    -0.68
     specificity
    -0.68
    POSITIVE LOGITS
     Dickinson
    1.10
     Lak
    0.98
    gdala
    0.90
    otte
    0.87
    pton
    0.83
    endi
    0.78
    issance
    0.75
    sburg
    0.75
     Ago
    0.74
    ãĤ£
    0.73
    Act Density 0.015%

    No Known Activations