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

    Neuronpedia

    INDEX
    Explanations

    terms related to denying or restriction of rights and access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ec
    -0.80
    oiler
    -0.79
    psc
    -0.79
    ================================
    -0.74
    è¦ļéĨĴ
    -0.73
    ARCH
    -0.73
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.71
    seed
    -0.70
    enegger
    -0.70
    rouse
    -0.68
    POSITIVE LOGITS
     access
    0.80
     gratification
    0.73
     refunds
    0.71
    ļéĨĴ
    0.70
    lement
    0.70
     outright
    0.70
     receipt
    0.69
    afe
    0.68
     him
    0.67
     them
    0.67
    Act Density 0.011%

    No Known Activations