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

    Neuronpedia

    INDEX
    Explanations

    references to specific demographics and categories of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.15
     Nou
    -0.14
    ób
    -0.14
    AU
    -0.14
    ifact
    -0.14
    unes
    -0.14
    ries
    -0.13
     Chim
    -0.13
    pendicular
    -0.13
    imple
    -0.13
    POSITIVE LOGITS
    eya
    0.17
    ľ
    0.15
     Hollow
    0.14
    çļ
    0.14
    ëŀĺìĬ¤
    0.14
     Bender
    0.13
    893
    0.13
    Mixed
    0.13
    ktop
    0.13
    igned
    0.13
    Act Density 0.013%

    No Known Activations