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

    Neuronpedia

    INDEX
    Explanations

    mentions of presidents and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to presidents and presidential context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.79
    INGTON
    -0.63
    ells
    -0.63
    potion
    -0.62
     Squid
    -0.62
     Kara
    -0.62
    Wo
    -0.61
     mats
    -0.61
     Scene
    -0.60
    bidden
    -0.59
    POSITIVE LOGITS
    hips
    1.33
    hip
    1.19
     whom
    0.98
     administrations
    0.93
     elected
    0.92
     appointed
    0.91
     appoint
    0.89
     who
    0.89
    clinton
    0.88
    elected
    0.88
    Act Density 0.174%

    No Known Activations