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

    Neuronpedia

    INDEX
    Explanations

    references to couples and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adil
    -0.20
    ummings
    -0.18
    ../../
    -0.17
    unner
    -0.15
    ulkan
    -0.14
    engin
    -0.14
    ried
    -0.14
    ionales
    -0.14
    asio
    -0.14
    upa
    -0.14
    POSITIVE LOGITS
    /group
    0.25
    /single
    0.24
    /groups
    0.23
     dozen
    0.20
     who
    0.20
    /part
    0.20
    hood
    0.20
    wares
    0.19
     whom
    0.18
    who
    0.18
    Act Density 0.014%

    No Known Activations