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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures, specifically focusing on mentions of Theodore Roosevelt

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Roosevelt" and its related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.74
    las
    -0.72
    semble
    -0.71
    LESS
    -0.70
    raints
    -0.69
    ateurs
    -0.66
    hem
    -0.66
    rav
    -0.65
    ning
    -0.64
    phabet
    -0.62
    POSITIVE LOGITS
     Roosevelt
    1.23
     mosqu
    0.92
    enthal
    0.92
    velt
    0.82
    iets
    0.79
    hower
    0.77
    éĹĺ
    0.76
    enstein
    0.75
    dinand
    0.72
    udeau
    0.71
    Act Density 0.011%

    No Known Activations