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

    Neuronpedia

    INDEX
    Explanations

    words related to occupancy and occupation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bordada
    -0.44
     impreso
    -0.39
     Freundin
    -0.38
     excelencia
    -0.38
     artesanales
    -0.37
     mijne
    -0.37
     bendera
    -0.36
     autorité
    -0.36
     elétrico
    -0.36
     meisjes
    -0.36
    POSITIVE LOGITS
     Occup
    0.90
    Occup
    0.80
     occupy
    0.80
    occup
    0.76
     occup
    0.75
     normal
    0.71
     occupies
    0.71
     occupying
    0.70
     idle
    0.69
    normal
    0.69
    Act Density 0.204%

    No Known Activations