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

    Neuronpedia

    INDEX
    Explanations

    references to the physicist Albert Einstein

    oai_token-act-pair · gpt-3.5-turbo

    references to Albert Einstein

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.88
    elcome
    -0.80
    ãĥ¯
    -0.79
    ned
    -0.78
    ning
    -0.77
    efully
    -0.76
    mble
    -0.73
    osuke
    -0.73
    pter
    -0.72
    ners
    -0.71
    POSITIVE LOGITS
     Einstein
    1.12
     Calder
    0.83
     Schwe
    0.75
     Pu
    0.74
    inas
    0.70
     Hammond
    0.69
    inates
    0.68
    onso
    0.68
    rand
    0.67
     Heights
    0.67
    Act Density 0.014%

    No Known Activations