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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locking mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to locking mechanisms or security systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.82
    LV
    -0.77
    OTAL
    -0.67
    resso
    -0.66
    schild
    -0.66
    osed
    -0.64
    acio
    -0.64
    aukee
    -0.62
    ãĤ¡
    -0.62
     Goals
    -0.62
    POSITIVE LOGITS
    picking
    1.27
    heed
    1.18
    pick
    1.09
    creen
    1.03
    hart
    0.98
    lear
    0.95
    downs
    0.90
     horns
    0.89
    door
    0.89
    yer
    0.88
    Act Density 0.016%

    No Known Activations