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

    Neuronpedia

    INDEX
    Explanations

    phrases related to large amounts or significant levels of something

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating significant quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.75
    relations
    -0.73
     Reincarn
    -0.70
     Siber
    -0.68
    minist
    -0.65
    agents
    -0.64
     Contin
    -0.64
    iche
    -0.64
    sim
    -0.64
    istar
    -0.63
    POSITIVE LOGITS
     hefty
    1.11
     chunk
    0.93
     bucks
    0.82
     notch
    0.77
    bilt
    0.77
     pric
    0.74
     tracts
    0.70
     whopping
    0.70
    uador
    0.70
     dow
    0.69
    Act Density 0.023%

    No Known Activations