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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles and traffic-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yro
    -0.18
    460
    -0.15
    utron
    -0.14
    995
    -0.14
    685
    -0.14
    ÄĻk
    -0.13
    enger
    -0.13
     onBind
    -0.13
    ropp
    -0.13
    lesia
    -0.13
    POSITIVE LOGITS
    олоÑģ
    0.17
    hrad
    0.15
    gfx
    0.15
     McGu
    0.15
    jam
    0.14
    .hd
    0.14
    ui
    0.14
    odus
    0.14
     СÑĥд
    0.14
    umas
    0.13
    Act Density 0.100%

    No Known Activations