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

    Neuronpedia

    INDEX
    Explanations

    the word "Hamilton."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Hamilton"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.90
    lihood
    -0.84
    RAM
    -0.76
    gger
    -0.73
    scription
    -0.71
    lect
    -0.70
    vg
    -0.70
    ongyang
    -0.68
    eker
    -0.68
    unal
    -0.67
    POSITIVE LOGITS
    pton
    0.85
    Hamilton
    0.83
     Hamilton
    0.81
    enburg
    0.78
    igans
    0.77
     Gardens
    0.74
     County
    0.73
    enberg
    0.72
     Place
    0.71
    ians
    0.70
    Act Density 0.029%

    No Known Activations