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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movement

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement and physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£
    -0.66
    ?????-
    -0.66
    blogspot
    -0.64
    archives
    -0.63
    Ranked
    -0.59
    士
    -0.59
     Palestin
    -0.59
    failed
    -0.58
    DonaldTrump
    -0.57
    otten
    -0.57
    POSITIVE LOGITS
     downstairs
    1.55
     upstairs
    1.44
     closer
    1.17
     toward
    1.16
     towards
    1.15
     inside
    1.11
     up
    1.08
     onstage
    1.04
     backstage
    1.03
     nearer
    1.01
    Act Density 0.133%

    No Known Activations