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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.18
    aber
    -0.15
    ayne
    -0.15
    ìľ¨
    -0.14
    ¼åIJĪ
    -0.14
    mada
    -0.14
    side
    -0.14
    ï¸ı
    -0.14
    оÑģÑĤ
    -0.14
    most
    -0.14
    POSITIVE LOGITS
     who
    0.18
    /entities
    0.17
    /groups
    0.15
    asion
    0.14
    oucher
    0.14
     Cruiser
    0.13
    AMI
    0.13
    TION
    0.13
    /entity
    0.13
    _joint
    0.13
    Act Density 0.112%

    No Known Activations