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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations

    oai_token-act-pair · gpt-3.5-turbo

    HTML list item elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Debor
    -0.72
    mble
    -0.72
    eers
    -0.71
     Cosponsors
    -0.68
    Ĥ¬
    -0.68
    lain
    -0.68
    rations
    -0.67
    manship
    -0.66
    rated
    -0.66
    locks
    -0.66
    POSITIVE LOGITS
    utenant
    1.25
    zzle
    1.22
    ptin
    1.08
    udic
    0.98
    ars
    0.97
    uci
    0.93
    veland
    0.93
    pton
    0.92
    pper
    0.91
    plom
    0.91
    Act Density 0.013%

    No Known Activations