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

    Neuronpedia

    INDEX
    Explanations

    references to community engagement and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wife
    -0.17
    wife
    -0.17
    ed
    -0.16
     themselves
    -0.16
    гл
    -0.15
    deg
    -0.15
    iled
    -0.15
    妻
    -0.15
     solo
    -0.15
    och
    -0.14
    POSITIVE LOGITS
     selves
    0.31
    tesy
    0.29
     lives
    0.28
     ourselves
    0.27
    SEL
    0.27
     bodies
    0.24
     hearts
    0.23
     dear
    0.23
     Lives
    0.23
     mutual
    0.22
    Act Density 0.236%

    No Known Activations