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

    Neuronpedia

    INDEX
    Explanations

    references to specific political figures, particularly former presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to former political leaders and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.67
    urat
    -0.65
    itivity
    -0.64
    igs
    -0.63
     beh
    -0.63
    ickle
    -0.62
    ointment
    -0.61
     fingert
    -0.61
    ciation
    -0.61
    illy
    -0.61
    POSITIVE LOGITS
     Yugoslavia
    0.79
     Desmond
    0.74
    ãĤ¶
    0.73
    turned
    0.69
     Olympia
    0.65
     Biden
    0.63
    oslov
    0.63
     Lyndon
    0.62
    bilt
    0.62
    ģĸ
    0.61
    Act Density 0.154%

    No Known Activations