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

    Neuronpedia

    INDEX
    Explanations

    references to celebrities and fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paragus
    -0.17
    izu
    -0.17
    ;element
    -0.17
    zon
    -0.16
    ROLS
    -0.16
    OfWork
    -0.16
    /devices
    -0.15
     ÄĮer
    -0.15
    shed
    -0.15
    adesh
    -0.15
    POSITIVE LOGITS
     chef
    0.23
    -status
    0.21
     Cru
    0.20
     endorsements
    0.20
     status
    0.19
     Chef
    0.19
     Sight
    0.19
     spotting
    0.19
     sighting
    0.18
    hood
    0.18
    Act Density 0.009%

    No Known Activations