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

    Neuronpedia

    INDEX
    Explanations

    names or titles of political figures and their aides

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "aide" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sabha
    -0.73
    Population
    -0.71
    MQ
    -0.71
    EVA
    -0.70
    istic
    -0.67
    itiveness
    -0.67
    PATH
    -0.67
    aval
    -0.64
    ategory
    -0.62
     bilateral
    -0.62
    POSITIVE LOGITS
     Huma
    1.06
     aide
    0.86
     tasked
    0.76
     counsel
    0.75
     aides
    0.73
     staffer
    0.72
    maid
    0.71
    hene
    0.71
     confid
    0.69
    ster
    0.69
    Act Density 0.054%

    No Known Activations