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

    Neuronpedia

    INDEX
    Explanations

    references to the number four and related numerical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     some
    -0.14
    SENS
    -0.13
    DT
    -0.13
     forum
    -0.13
    phin
    -0.13
     More
    -0.13
     numerous
    -0.13
    ichtet
    -0.13
     stuff
    -0.13
     two
    -0.13
    POSITIVE LOGITS
    acity
    0.17
    ikon
    0.17
    acom
    0.17
    teenth
    0.17
    ControlEvents
    0.15
    UrlParser
    0.15
    /Dk
    0.15
    parate
    0.15
    lü
    0.15
    fold
    0.14
    Act Density 0.081%

    No Known Activations