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

    Neuronpedia

    INDEX
    Explanations

    references to recurring patterns or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onaut
    -0.18
    ód
    -0.15
    omer
    -0.14
    ož
    -0.14
    /slick
    -0.14
    anh
    -0.14
    orb
    -0.14
    atch
    -0.14
    ãĥ³ãĥ
    -0.13
    erm
    -0.13
    POSITIVE LOGITS
    igrams
    0.17
    okin
    0.15
    ÑİÑĢ
    0.15
    pch
    0.15
    ãĥªãĥ¼ãĤº
    0.14
     Olson
    0.14
    agara
    0.14
     Bite
    0.14
    .documentation
    0.14
    evice
    0.14
    Act Density 0.369%

    No Known Activations