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

    Neuronpedia

    INDEX
    Explanations

    references to job roles and professional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Offices
    -0.17
     offices
    -0.15
    ÑĨÑİ
    -0.14
    dv
    -0.14
    ifar
    -0.14
    uros
    -0.14
    DAC
    -0.14
    allee
    -0.14
    adiator
    -0.14
     factory
    -0.13
    POSITIVE LOGITS
     Servers
    0.30
     servers
    0.29
    Servers
    0.27
     bart
    0.25
    /server
    0.25
    -server
    0.24
     server
    0.24
     serving
    0.23
     Server
    0.23
    -service
    0.23
    Act Density 0.168%

    No Known Activations