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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or mobility

    oai_token-act-pair · gpt-3.5-turbo

    references to physical actions and mobility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -1.00
     commenter
    -0.79
     buyer
    -0.75
     jurisd
    -0.71
     Seller
    -0.70
     bidder
    -0.67
     reviewer
    -0.67
    ãĥį
    -0.64
     Outbreak
    -0.63
     Ans
    -0.62
    POSITIVE LOGITS
     uphill
    1.22
     upright
    1.19
     indoors
    1.14
     outdoors
    1.14
     stairs
    1.13
     backwards
    1.09
     sideways
    1.09
     downhill
    1.07
     awkwardly
    1.01
     excessively
    1.00
    Act Density 0.267%

    No Known Activations