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

    Neuronpedia

    INDEX
    Explanations

    actions related to physically fastening things together

    oai_token-act-pair · gpt-3.5-turbo

    actions related to restraining or attaching objects and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Plaza
    -0.74
     Carbuncle
    -0.73
    earances
    -0.64
    conom
    -0.63
    ordan
    -0.63
    rogens
    -0.62
     Scotia
    -0.62
    ciation
    -0.61
    uary
    -0.60
    rien
    -0.60
    POSITIVE LOGITS
     onto
    0.96
     down
    0.86
     tightly
    0.82
    lock
    0.80
     together
    0.80
     tight
    0.75
    ciating
    0.75
    stick
    0.75
    ged
    0.75
    tail
    0.74
    Act Density 0.133%

    No Known Activations