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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sitting or being stationary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kase
    -0.66
     lemp
    -0.65
     maksi
    -0.63
     uhr
    -0.62
     kela
    -0.61
     kaos
    -0.61
     kasa
    -0.60
     osal
    -0.59
     Præ
    -0.59
     kram
    -0.59
    POSITIVE LOGITS
     sit
    1.28
     sitting
    1.17
     sat
    1.08
     sits
    1.07
    sit
    1.06
    Sit
    1.05
     Sit
    1.04
    sitting
    1.04
    Sitting
    0.96
     SIT
    0.95
    Act Density 0.096%

    No Known Activations