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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly "Nate."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on the name "Nate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iance
    -1.07
    loo
    -0.97
    iances
    -0.91
    ijk
    -0.86
    ily
    -0.82
    osite
    -0.79
    usc
    -0.77
    stadt
    -0.74
    ies
    -0.74
    aunder
    -0.74
    POSITIVE LOGITS
    IELD
    0.77
    heastern
    0.75
    hower
    0.71
    ãĤ¡
    0.69
    BLIC
    0.65
     Manson
    0.65
    eor
    0.64
    ÃįÃį
    0.64
    ppo
    0.63
     Niet
    0.62
    Act Density 0.078%

    No Known Activations