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

    Neuronpedia

    INDEX
    Explanations

    references to Mexico and Mexican-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aic
    -0.17
    lier
    -0.15
    ye
    -0.15
    ëĭĿ
    -0.15
    ly
    -0.15
    nings
    -0.15
    yer
    -0.15
    itive
    -0.15
    arde
    -0.15
    ala
    -0.14
    POSITIVE LOGITS
     City
    0.35
     CITY
    0.26
    City
    0.25
    -city
    0.19
     city
    0.19
    abay
    0.18
    icans
    0.18
    perience
    0.17
    _CITY
    0.17
    åŁİ
    0.17
    Act Density 0.019%

    No Known Activations