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

    Neuronpedia

    INDEX
    Explanations

    terms related to workplace safety violations and hazards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼¾
    -0.15
    abwe
    -0.15
    cls
    -0.15
    694
    -0.14
    agn
    -0.14
     nod
    -0.14
    719
    -0.13
     Beds
    -0.13
     Tort
    -0.13
    yas
    -0.13
    POSITIVE LOGITS
     employer
    0.18
     fatally
    0.18
     energ
    0.18
    employer
    0.17
     employers
    0.17
    Powered
    0.17
     Employer
    0.17
     Powered
    0.16
    Employees
    0.15
     Energ
    0.15
    Act Density 0.046%

    No Known Activations