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

    Neuronpedia

    INDEX
    Explanations

    references to a specific subject or entity, denoted as "utt"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.72
    xiety
    -0.62
     retri
    -0.61
    ã
    -0.60
     lottery
    -0.60
     corros
    -0.59
    cit
    -0.59
     streamed
    -0.58
    phy
    -0.58
     surn
    -0.58
    POSITIVE LOGITS
    erella
    1.20
    iful
    0.95
    aneous
    0.94
    ierrez
    0.93
    gart
    0.91
    anium
    0.90
    oggle
    0.89
    elta
    0.87
    ifully
    0.87
    aneers
    0.87
    Act Density 0.032%

    No Known Activations