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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Graham."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.86
    puter
    -0.84
    cles
    -0.82
    bec
    -0.70
    ————————
    -0.69
    senal
    -0.68
    ngth
    -0.67
    haps
    -0.67
    ting
    -0.65
    PLA
    -0.65
    POSITIVE LOGITS
    iday
    0.84
    esse
    0.82
    wagen
    0.81
     Greene
    0.78
     Graham
    0.75
    Cass
    0.73
     Hancock
    0.72
    enstein
    0.70
    gren
    0.69
    abba
    0.69
    Act Density 0.028%

    No Known Activations