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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "returning" or "reverting" to a previous state or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udic
    -0.16
    uÄį
    -0.15
    372
    -0.15
    á»ı
    -0.14
    esses
    -0.14
     abide
    -0.14
    eniz
    -0.14
    isine
    -0.14
     sake
    -0.14
    utin
    -0.14
    POSITIVE LOGITS
    wards
    0.30
    slash
    0.26
    ronym
    0.23
    slashes
    0.22
    WARDS
    0.20
    lashes
    0.18
    gam
    0.18
    ward
    0.18
    scatter
    0.18
     wards
    0.17
    Act Density 0.082%

    No Known Activations