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

    Neuronpedia

    INDEX
    Explanations

    Keywords related to gates or gatekeeping

    oai_token-act-pair · gpt-3.5-turbo

    references to gates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.96
     Hots
    -0.89
    ensional
    -0.76
    lihood
    -0.75
    enegger
    -0.75
    ocre
    -0.68
    issance
    -0.66
    ulously
    -0.65
     Norm
    -0.65
    ulous
    -0.64
    POSITIVE LOGITS
    keepers
    1.29
    keeper
    1.22
    ways
    1.08
     gates
    1.01
    posts
    0.98
    stones
    0.98
    keeping
    0.96
    house
    0.94
     gate
    0.94
    staff
    0.93
    Act Density 0.009%

    No Known Activations