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

    Neuronpedia

    INDEX
    Explanations

    elements related to health and safety measures in a workplace context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _BLK
    -0.15
     imprison
    -0.15
    okus
    -0.15
    ï¼Īå¹³æĪIJ
    -0.14
    avad
    -0.14
    ollar
    -0.14
    tsy
    -0.14
    REAK
    -0.13
    ULO
    -0.13
    QueryBuilder
    -0.13
    POSITIVE LOGITS
     socially
    0.30
     social
    0.30
    social
    0.28
     distancing
    0.28
     mask
    0.27
    -social
    0.27
    _social
    0.26
    Social
    0.26
     Masks
    0.25
    -mask
    0.25
    Act Density 0.055%

    No Known Activations