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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts, often emphasizing its presence in different phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.18
    atrix
    -0.17
     PartialView
    -0.16
    äm
    -0.15
    ATRIX
    -0.15
    ROP
    -0.14
    allax
    -0.14
    ем
    -0.13
    bole
    -0.13
    eriod
    -0.13
    POSITIVE LOGITS
    eft
    0.16
    aring
    0.16
    insky
    0.16
    /cs
    0.15
    ingham
    0.15
    owing
    0.15
    uper
    0.14
    abay
    0.14
    ikk
    0.14
    .asc
    0.14
    Act Density 0.005%

    No Known Activations