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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Sup" and its variations, indicating a focus on supervisory or supporting roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Margins
    -0.16
    ypad
    -0.16
    ystone
    -0.16
    readcr
    -0.16
    tags
    -0.15
     Bair
    -0.15
    iness
    -0.15
    üst
    -0.15
    èĢ
    -0.15
    auge
    -0.14
    POSITIVE LOGITS
    posed
    0.20
     sup
    0.20
    posing
    0.17
    intendent
    0.17
    urb
    0.16
    à¹Ģà¸Ľà¸Ńร
    0.16
    ois
    0.16
    annah
    0.16
    ervisor
    0.16
    pose
    0.15
    Act Density 0.019%

    No Known Activations