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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isbury
    -0.15
    berger
    -0.15
     strat
    -0.14
     ç§ĭ
    -0.14
    ıy
    -0.14
    utzer
    -0.14
    анÑĸз
    -0.14
     synthes
    -0.14
    onna
    -0.13
    ixed
    -0.13
    POSITIVE LOGITS
     Jenner
    0.28
     Kardashian
    0.27
     Kim
    0.26
     Kardash
    0.23
    Kim
    0.23
     Kendall
    0.21
     Keeping
    0.20
     kim
    0.19
     kims
    0.18
     jen
    0.18
    Act Density 0.016%

    No Known Activations