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

    Neuronpedia

    INDEX
    Explanations

    references to positions of leadership and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.17
    grily
    -0.16
    indow
    -0.15
    ive
    -0.15
    dal
    -0.15
    burgh
    -0.15
    ogle
    -0.15
    ogan
    -0.14
    los
    -0.14
    ennes
    -0.14
    POSITIVE LOGITS
    person
    0.20
    ../../../
    0.17
    lld
    0.17
    rig
    0.17
    lotte
    0.16
    ships
    0.16
    izoph
    0.16
     <!--[
    0.16
    board
    0.16
    boards
    0.15
    Act Density 0.019%

    No Known Activations