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

    Neuronpedia

    INDEX
    Explanations

    book titles

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by" followed by an author's name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptions
    -0.87
    ptive
    -0.81
    illance
    -0.75
    SPONSORED
    -0.73
    ption
    -0.71
    igrate
    -0.71
    });
    -0.70
    inea
    -0.70
    bia
    -0.70
    antle
    -0.69
    POSITIVE LOGITS
     virtue
    1.07
     Edwin
    0.89
    akuya
    0.87
     Jorge
    0.84
     Johann
    0.83
     Jonathan
    0.83
     Pablo
    0.83
     Zed
    0.83
     Hilton
    0.83
     Gerald
    0.82
    Act Density 0.109%

    No Known Activations