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

    Neuronpedia

    INDEX
    Explanations

    references to government positions and councils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guru
    -0.69
     guru
    -0.62
     NX
    -0.61
     Stick
    -0.61
    edIn
    -0.59
     Augustus
    -0.59
    DonaldTrump
    -0.59
    大
    -0.58
     Ghostbusters
    -0.58
     Leader
    -0.58
    POSITIVE LOGITS
     Photograph
    0.73
    mage
    0.71
    catentry
    0.71
    sic
    0.71
    work
    0.70
    vironment
    0.69
    stuff
    0.69
    ossibility
    0.68
    usional
    0.68
    matter
    0.67
    Act Density 0.240%

    No Known Activations