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

    Neuronpedia

    INDEX
    Explanations

    measurements of height and length

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    measurements of objects in feet followed by numbers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    sell
    -0.66
    PsyNetMessage
    -0.66
    itans
    -0.65
    uner
    -0.64
    ifiable
    -0.64
    astically
    -0.62
    ulla
    -0.62
     Synd
    -0.61
    acco
    -0.61
    udeb
    -0.61
    POSITIVE LOGITS
    steps
    0.84
    foot
    0.81
    wear
    0.81
    step
    0.80
    lihood
    0.77
    prints
    0.74
    Tree
    0.74
    Foot
    0.74
    loo
    0.73
    feet
    0.72
    Act Density 0.006%

    No Known Activations