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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Beth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.89
    00007
    -0.79
    xual
    -0.75
    agents
    -0.69
    aeda
    -0.66
    Executive
    -0.66
     fixation
    -0.65
    eers
    -0.64
     ACTION
    -0.62
    intent
    -0.61
    POSITIVE LOGITS
    lehem
    1.23
     Beth
    1.17
    terness
    0.91
    urst
    0.90
    ode
    0.79
    ãĤ¡
    0.79
    anie
    0.78
     Coh
    0.78
     Anne
    0.76
    ®
    0.76
    Act Density 0.005%

    No Known Activations