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

    Neuronpedia

    INDEX
    Explanations

    references to various types of dips or similar food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uge
    -0.16
     tug
    -0.14
    ched
    -0.14
    ç·Ĵ
    -0.14
    amation
    -0.14
    /Runtime
    -0.14
    ιÏİ
    -0.14
    redd
    -0.14
    hod
    -0.14
    UGE
    -0.14
    POSITIVE LOGITS
     Dip
    0.24
     dip
    0.22
    acus
    0.19
    ity
    0.17
    stick
    0.17
    per
    0.17
    hen
    0.16
    utar
    0.16
     Dipl
    0.16
    sticks
    0.16
    Act Density 0.013%

    No Known Activations