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

    Neuronpedia

    INDEX
    Explanations

    words indicating change or replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indow
    -0.16
    loth
    -0.16
    DDR
    -0.15
    iguous
    -0.14
     tape
    -0.14
    licative
    -0.14
    eriod
    -0.14
    legate
    -0.14
    BOSE
    -0.14
     Spin
    -0.14
    POSITIVE LOGITS
    åĿĬ
    0.17
    .LoggerFactory
    0.14
    ädchen
    0.14
    otos
    0.14
     repro
    0.14
     trá»įng
    0.13
    uibModal
    0.13
     Benn
    0.13
    ockets
    0.12
     Subscriber
    0.12
    Act Density 0.000%

    No Known Activations