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

    Neuronpedia

    INDEX
    Explanations

    terms related to race performance and standings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outes
    -0.15
    åľŃ
    -0.14
    @@
    -0.14
    ois
    -0.14
    usi
    -0.14
    PLL
    -0.14
    @student
    -0.14
    grav
    -0.13
    oss
    -0.13
    low
    -0.13
    POSITIVE LOGITS
    pyx
    0.16
    ãĤīãģĦ
    0.16
    ornings
    0.15
     Kramer
    0.15
     Bent
    0.15
    gid
    0.14
     Ars
    0.14
    rys
    0.13
     Gro
    0.13
    nyder
    0.13
    Act Density 0.092%

    No Known Activations