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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating multiple occurrences or levels of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MPI
    -0.16
     [/
    -0.15
    ayah
    -0.15
    Way
    -0.15
     Ten
    -0.15
    rary
    -0.14
    zc
    -0.14
    .rf
    -0.14
    andWhere
    -0.14
    STALL
    -0.14
    POSITIVE LOGITS
    ouv
    0.17
    croft
    0.16
    oux
    0.16
     RoundedRectangle
    0.15
    oker
    0.14
    олÑİ
    0.14
    Äĩi
    0.14
    epad
    0.14
     Alv
    0.14
     Dynam
    0.14
    Act Density 0.081%

    No Known Activations