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

    Neuronpedia

    INDEX
    Explanations

    the name "Joe" followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Joe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.89
    mble
    -0.87
    igators
    -0.84
    hips
    -0.82
    NESS
    -0.79
    igator
    -0.75
    raints
    -0.74
    igated
    -0.74
    chwitz
    -0.71
    rights
    -0.71
    POSITIVE LOGITS
     Biden
    0.94
     Arpaio
    0.88
     Rog
    0.82
    zzi
    0.82
    ppo
    0.82
    xtap
    0.78
     Danger
    0.76
    pport
    0.76
     Walsh
    0.74
     Scarborough
    0.73
    Act Density 0.013%

    No Known Activations