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

    Neuronpedia

    INDEX
    Explanations

    elements of code related to user input and interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.15
    st
    -0.15
    qu
    -0.14
    wend
    -0.14
     Brother
    -0.14
    th
    -0.14
     Hol
    -0.14
    gee
    -0.13
     Dra
    -0.13
     brother
    -0.13
    POSITIVE LOGITS
    arkan
    0.17
    Backdrop
    0.17
    plemented
    0.17
    rrha
    0.16
    sian
    0.15
    onium
    0.15
    atik
    0.15
    amarin
    0.15
    sse
    0.15
    .VERSION
    0.15
    Act Density 0.011%

    No Known Activations