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

    Neuronpedia

    INDEX
    Explanations

    references to loved ones and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.15
     defaultMessage
    -0.15
    адки
    -0.14
    icina
    -0.14
    kova
    -0.14
    ufen
    -0.14
     Opport
    -0.13
    ủy
    -0.13
    lem
    -0.13
    rait
    -0.13
    POSITIVE LOGITS
     ones
    0.50
     Ones
    0.38
    ones
    0.33
    .ones
    0.26
    ONES
    0.21
     relative
    0.20
    relative
    0.20
     once
    0.18
     Once
    0.18
    onest
    0.17
    Act Density 0.008%

    No Known Activations