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

    Neuronpedia

    INDEX
    Explanations

    references to nationalities or ethnic identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.17
     own
    -0.16
    706
    -0.16
    omor
    -0.15
    awe
    -0.15
    /trunk
    -0.14
     Dra
    -0.14
    ss
    -0.14
    atar
    -0.14
    iece
    -0.14
    POSITIVE LOGITS
    ertz
    0.17
    Ä±ÅŁÄ±k
    0.15
     bench
    0.15
    .Generated
    0.15
    ห
    0.15
    ppe
    0.14
    ERSHEY
    0.14
    ezi
    0.14
    ooth
    0.14
    меÑģÑĤ
    0.14
    Act Density 0.147%

    No Known Activations