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

    Neuronpedia

    INDEX
    Explanations

    text related to technical skills and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to reading habits and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Robertson
    -0.60
    Secretary
    -0.57
     Joint
    -0.57
     Teresa
    -0.56
    Donald
    -0.56
     1921
    -0.55
     summed
    -0.55
     1954
    -0.54
     assassinated
    -0.54
     Cosponsors
    -0.54
    POSITIVE LOGITS
    )).
    1.00
    .).
    0.85
     otherwise
    0.85
    ).
    0.78
    !).
    0.76
    %).
    0.75
    ?).
    0.73
    }.
    0.69
    %.
    0.69
    livion
    0.67
    Act Density 1.605%

    No Known Activations