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

    Neuronpedia

    INDEX
    Explanations

    various types of publication and attribution information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rita
    -0.15
    zen
    -0.14
    en
    -0.13
    ãĥĽ
    -0.13
    /chart
    -0.12
    ella
    -0.12
     Route
    -0.12
    zan
    -0.12
    ään
    -0.12
    ÑĢави
    -0.12
    POSITIVE LOGITS
    readcr
    0.17
    oÄŁ
    0.15
    ripp
    0.15
    gst
    0.14
    iday
    0.14
    åĿĬ
    0.13
    ertext
    0.13
    gw
    0.13
    ipi
    0.13
     "/"↵
    0.13
    Act Density 0.101%

    No Known Activations