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

    Neuronpedia

    INDEX
    Explanations

    contraction-based phrases indicating exclusion or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stops
    -0.16
    oyer
    -0.15
    bject
    -0.15
    uit
    -0.15
    gratis
    -0.14
    iman
    -0.14
    uy
    -0.13
    ủy
    -0.13
     (;;
    -0.13
    .DataVisualization
    -0.13
    POSITIVE LOGITS
    ysi
    0.16
    atk
    0.15
     ÙħتÙģ
    0.14
    atti
    0.14
    aben
    0.14
    isos
    0.14
    ÌĨ
    0.14
    iki
    0.14
    á»ĩn
    0.13
    uae
    0.13
    Act Density 0.011%

    No Known Activations