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

    Neuronpedia

    INDEX
    Explanations

    topics related to decision-making processes involving various factors, including technology, justice, and energy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     portion
    -0.15
    -0.15
    728
    -0.15
    sto
    -0.15
    άÏĥ
    -0.14
     heart
    -0.14
    inn
    -0.14
    urus
    -0.14
    ela
    -0.14
     degree
    -0.14
    POSITIVE LOGITS
     affair
    0.28
     thing
    0.23
     Thing
    0.23
    çļĦäºĭ
    0.21
     phenomenon
    0.20
    Thing
    0.20
     thang
    0.19
     phenomena
    0.19
     problem
    0.17
     issue
    0.17
    Act Density 0.213%

    No Known Activations