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

    Neuronpedia

    INDEX
    Explanations

    references to Social Security and related benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gu
    -0.16
    ymoon
    -0.15
    erez
    -0.15
    ackbar
    -0.15
    ób
    -0.15
     ÑĢазмеÑī
    -0.14
     Ãľl
    -0.14
    avel
    -0.14
    PIO
    -0.14
    ixels
    -0.14
    POSITIVE LOGITS
     Social
    0.39
    Social
    0.34
     SOCIAL
    0.29
     disability
    0.29
     social
    0.28
     SSA
    0.27
     Disability
    0.26
    social
    0.24
     SSD
    0.23
     disabled
    0.22
    Act Density 0.016%

    No Known Activations