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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the idea of boundaries and limitations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDA
    -0.17
    loat
    -0.17
    rana
    -0.15
    çģ
    -0.14
    ewan
    -0.14
    rib
    -0.14
    tru
    -0.14
     sÃłng
    -0.14
    -roll
    -0.14
    mux
    -0.14
    POSITIVE LOGITS
     boundaries
    0.20
     bounds
    0.18
     borders
    0.17
    gren
    0.15
    ForMember
    0.15
    bounds
    0.14
     Bounds
    0.14
    _bounds
    0.14
    íĭĢ
    0.14
    евого
    0.14
    Act Density 0.063%

    No Known Activations