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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Mandelt" with varied activations around how closely it matches the expected term, and other associated variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mandelbrot" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Charges
    -0.76
    ãģį
    -0.73
    CLOSE
    -0.70
    terday
    -0.69
     Typhoon
    -0.66
     Spit
    -0.64
     yours
    -0.61
    prime
    -0.61
    ï¸
    -0.61
    spective
    -0.60
    POSITIVE LOGITS
    olin
    1.15
    rake
    1.03
    arine
    1.00
    eer
    0.94
    erella
    0.92
    arin
    0.92
    ele
    0.92
    een
    0.92
    atory
    0.91
    ingo
    0.90
    Act Density 0.018%

    No Known Activations