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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts indicating a 'setting' or 'establishment' of scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.18
    WARDS
    -0.17
    ÙĪÙĦÙĩ
    -0.16
    dera
    -0.15
    ushima
    -0.15
    kud
    -0.15
    quito
    -0.15
    .liferay
    -0.15
    ULATE
    -0.15
    426
    -0.15
    POSITIVE LOGITS
     apart
    0.29
     loose
    0.28
     aside
    0.27
     sail
    0.26
     abl
    0.24
     forth
    0.24
     fair
    0.22
     against
    0.22
    zt
    0.22
    -piece
    0.22
    Act Density 0.018%

    No Known Activations