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

    Neuronpedia

    INDEX
    Explanations

    words related to gates and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.97
     Hots
    -0.82
    issance
    -0.82
    lihood
    -0.77
    ensional
    -0.75
    TING
    -0.70
    nces
    -0.69
    encers
    -0.66
    arus
    -0.66
    ynasty
    -0.64
    POSITIVE LOGITS
    keepers
    1.38
    keeper
    1.32
    ways
    1.17
    posts
    1.07
    keeping
    1.07
    stones
    1.00
    house
    0.93
     gates
    0.91
    fold
    0.90
    bell
    0.88
    Act Density 0.008%

    No Known Activations