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

    Neuronpedia

    INDEX
    Explanations

    the word "All" and its various forms used in relation to groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.17
    ovich
    -0.17
    etrain
    -0.16
    illions
    -0.16
    dz
    -0.15
    ä¹ĥ
    -0.15
    妮
    -0.15
    abilia
    -0.15
    etri
    -0.15
    emu
    -0.14
    POSITIVE LOGITS
    igator
    0.28
    geme
    0.24
    iance
    0.24
    igators
    0.23
    ignment
    0.23
    ergy
    0.22
    ahu
    0.22
    iances
    0.21
    igned
    0.21
    erdings
    0.21
    Act Density 0.058%

    No Known Activations