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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "aut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mary
    -0.73
    borough
    -0.70
    BLE
    -0.69
    nce
    -0.68
    WAY
    -0.66
    earchers
    -0.66
    MIT
    -0.66
    function
    -0.65
    mers
    -0.65
     Beir
    -0.63
    POSITIVE LOGITS
    ilus
    1.06
    emort
    1.02
    iful
    0.94
    umn
    0.91
    ographed
    0.90
    ograph
    0.90
    opsy
    0.90
    ica
    0.89
    ographs
    0.88
    ilia
    0.86
    Act Density 0.020%

    No Known Activations