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

    Neuronpedia

    INDEX
    Explanations

    references to traffic incidents and public safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uet
    -0.16
    offline
    -0.15
     Hidden
    -0.15
    pter
    -0.14
     offline
    -0.14
    iyah
    -0.14
    uth
    -0.14
     fed
    -0.13
     STAR
    -0.13
    iol
    -0.13
    POSITIVE LOGITS
    .simps
    0.17
    ummings
    0.17
    anka
    0.16
    ázd
    0.15
     Kendall
    0.15
    rint
    0.15
    emales
    0.14
    ecast
    0.14
    vation
    0.14
    èµ·
    0.14
    Act Density 0.306%

    No Known Activations