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

    Neuronpedia

    INDEX
    Explanations

    terms related to social structures and categories, particularly caste and class systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edge
    -0.15
    usat
    -0.15
    /Images
    -0.15
    steen
    -0.15
    MAP
    -0.15
    undry
    -0.15
    anitize
    -0.15
    å²³
    -0.14
    rodu
    -0.14
    ĢìĿ´
    -0.14
    POSITIVE LOGITS
     lat
    0.16
     above
    0.16
     th
    0.14
    æķħ
    0.14
     Ray
    0.14
     miss
    0.13
    ,
    0.13
     ÎĶε
    0.13
     spoilers
    0.13
     prob
    0.13
    Act Density 0.062%

    No Known Activations