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

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sik
    -0.16
    enga
    -0.15
    ManagerInterface
    -0.14
    -purpose
    -0.14
    Ñıл
    -0.14
    rish
    -0.14
    Ĭ
    -0.13
    ander
    -0.13
    aries
    -0.13
    ive
    -0.13
    POSITIVE LOGITS
    person
    0.28
    woman
    0.20
    persons
    0.18
    ../../../
    0.17
    manship
    0.17
    lift
    0.16
    urette
    0.16
    lotte
    0.16
    783
    0.16
    rig
    0.15
    Act Density 0.018%

    No Known Activations