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

    Neuronpedia

    INDEX
    Explanations

    references to positions of authority or roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bson
    -0.15
    ilden
    -0.15
    mlink
    -0.15
    insk
    -0.15
    arge
    -0.14
    dition
    -0.14
    ábado
    -0.14
    uset
    -0.14
    addock
    -0.14
    次
    -0.13
    POSITIVE LOGITS
     employment
    0.34
     employed
    0.33
    employed
    0.28
    employment
    0.26
     job
    0.26
     employee
    0.26
     worked
    0.25
     chez
    0.25
     work
    0.25
     working
    0.25
    Act Density 0.438%

    No Known Activations