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

    Neuronpedia

    INDEX
    Explanations

    references to collective ownership or communal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wife
    -0.20
    wife
    -0.17
     husband
    -0.15
    妻
    -0.15
     Wife
    -0.15
    ovit
    -0.15
    -wife
    -0.15
     career
    -0.15
    ed
    -0.14
    ools
    -0.14
    POSITIVE LOGITS
    tesy
    0.29
    SEL
    0.29
     ourselves
    0.29
     selves
    0.28
     lives
    0.28
     bodies
    0.25
     Lives
    0.24
     our
    0.24
     hearts
    0.24
     mutual
    0.23
    Act Density 0.221%

    No Known Activations