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

    Neuronpedia

    INDEX
    Explanations

    titles and roles related to leadership and authority positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orget
    -0.17
    audi
    -0.16
     konkrét
    -0.15
    ãĢħ
    -0.14
    unci
    -0.14
    isay
    -0.14
    curities
    -0.14
    aras
    -0.14
    ifecycle
    -0.14
    ilst
    -0.13
    POSITIVE LOGITS
     designate
    0.26
    åħ¼
    0.25
    ship
    0.23
     Emer
    0.23
    ships
    0.21
    ial
    0.19
    -elect
    0.18
    -design
    0.18
    SHIP
    0.18
    hips
    0.17
    Act Density 0.124%

    No Known Activations