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

    Neuronpedia

    INDEX
    Explanations

    references to saints and historical religious figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quito
    -0.17
     Santo
    -0.15
    adel
    -0.14
    erdem
    -0.14
    ando
    -0.14
    upe
    -0.14
    uggy
    -0.14
    ingo
    -0.14
    ernals
    -0.13
     Independ
    -0.13
    POSITIVE LOGITS
    phyl
    0.20
     Thr
    0.19
     Lydia
    0.19
     Ph
    0.17
     Asia
    0.16
     Petra
    0.16
     Syria
    0.15
     Memphis
    0.15
     Tham
    0.15
    apolis
    0.15
    Act Density 0.121%

    No Known Activations