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

    Neuronpedia

    INDEX
    Explanations

    references to the distribution of resources, wealth, and power

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mpeg
    -0.78
     Logged
    -0.75
    miah
    -0.72
    rompt
    -0.71
    lov
    -0.70
    ãĤ®
    -0.70
    poke
    -0.69
    ograp
    -0.68
    ideshow
    -0.66
    ocrates
    -0.66
    POSITIVE LOGITS
     responsibilities
    1.22
     blame
    1.12
     wealth
    1.09
     resources
    1.06
     responsibility
    1.06
     sexes
    1.02
     ownership
    1.01
     roles
    1.00
     workload
    1.00
     scarce
    0.99
    Act Density 0.163%

    No Known Activations