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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names, and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named Pierre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agy
    -0.83
    iband
    -0.76
    ighting
    -0.76
    ritten
    -0.75
    orld
    -0.75
    ichael
    -0.74
    astered
    -0.74
    awar
    -0.74
    izen
    -0.73
    ograp
    -0.73
    POSITIVE LOGITS
     Trudeau
    0.92
     rall
    0.80
    Ô
    0.79
    ued
    0.75
    Ò
    0.73
    loo
    0.72
    lez
    0.70
     Santana
    0.69
    xual
    0.69
     Laurent
    0.68
    Act Density 0.095%

    No Known Activations