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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "iron," particularly in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tam
    -0.18
    aney
    -0.17
    tas
    -0.17
    ea
    -0.17
    ermo
    -0.16
    ture
    -0.16
    ëŀį
    -0.16
    eyn
    -0.16
    arness
    -0.15
    led
    -0.15
    POSITIVE LOGITS
    ically
    0.32
    mong
    0.31
    workers
    0.29
     ore
    0.27
    worker
    0.27
    works
    0.26
    ical
    0.26
    cl
    0.25
     filings
    0.24
     Maiden
    0.24
    Act Density 0.016%

    No Known Activations