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

    Neuronpedia

    INDEX
    Explanations

    references to dowries and marriage practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    marriage and outside contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.35
    정
    -0.32
     dime
    -0.30
    rise
    -0.30
    core
    -0.29
    口
    -0.28
    替
    -0.27
    れて
    -0.27
    ise
    -0.26
     zlo
    -0.26
    POSITIVE LOGITS
     marriage
    0.76
    Marriage
    0.72
    marriage
    0.72
     dowry
    0.72
     Marriage
    0.69
     marry
    0.69
     Arranged
    0.66
     marrying
    0.66
     marriages
    0.63
     pengantin
    0.63
    Act Density 0.083%

    No Known Activations