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

    Neuronpedia

    INDEX
    Explanations

    the idea of something being unfathomable or difficult to understand

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "unfathomable" and the word "Did" as they relate to profound concepts and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newman
    -0.73
    feld
    -0.71
     prote
    -0.71
     Ludwig
    -0.66
     Stre
    -0.66
    egal
    -0.64
    aign
    -0.62
     mascul
    -0.62
     Albuquerque
    -0.62
     critic
    -0.62
    POSITIVE LOGITS
    athom
    2.06
    Did
    1.55
    ilateral
    1.17
     comprehension
    1.04
    Name
    0.91
    atable
    0.90
     comprehend
    0.84
    Was
    0.83
    pedia
    0.83
    ceivable
    0.82
    Act Density 0.059%

    No Known Activations