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

    Neuronpedia

    INDEX
    Explanations

    terms indicating consent or compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endar
    -0.14
    umer
    -0.14
     rub
    -0.14
     ÙĦÙĦس
    -0.14
     Bom
    -0.14
    رÙĪد
    -0.14
    styl
    -0.14
    uten
    -0.13
     Exped
    -0.13
    vertising
    -0.13
    POSITIVE LOGITS
    erva
    0.16
    ãģ¾ãģł
    0.15
    mma
    0.15
    akan
    0.15
     Merr
    0.14
    illian
    0.14
     ná
    0.14
     ont
    0.14
     pride
    0.14
    county
    0.14
    Act Density 0.002%

    No Known Activations