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

    Neuronpedia

    INDEX
    Explanations

    references to religious teachings or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.16
    aller
    -0.16
     Summers
    -0.15
     adequ
    -0.15
    agh
    -0.15
    áng
    -0.14
    ç®
    -0.13
     primes
    -0.13
    .Cross
    -0.13
    istrict
    -0.13
    POSITIVE LOGITS
    unca
    0.15
     erotische
    0.15
    rys
    0.15
     nackte
    0.15
    uxe
    0.14
     célib
    0.14
    antro
    0.14
    VERTISE
    0.13
    chants
    0.13
    274
    0.13
    Act Density 0.023%

    No Known Activations