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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zier
    -0.15
    rait
    -0.15
    eron
    -0.14
     Damen
    -0.14
    illon
    -0.14
     Vladim
    -0.13
    éĸĵ
    -0.13
    .openapi
    -0.13
    Massage
    -0.13
     Tradable
    -0.13
    POSITIVE LOGITS
     Smith
    0.29
    Smith
    0.27
     smith
    0.25
     Jones
    0.25
    smith
    0.20
    Jones
    0.20
    mith
    0.20
     Brown
    0.19
     Perez
    0.19
     Johns
    0.18
    Act Density 0.172%

    No Known Activations