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

    Neuronpedia

    INDEX
    Explanations

    specific JSON-like key-value pairs in a structured text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and structural elements in text, particularly JSON-like formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grades
    -0.68
     administr
    -0.67
     hoard
    -0.65
     abduct
    -0.65
     carp
    -0.62
     exch
    -0.62
     wealthier
    -0.62
    anmar
    -0.62
    £ı
    -0.61
     financially
    -0.60
    POSITIVE LOGITS
    thumbnails
    1.01
    taboola
    0.99
    english
    0.89
    BuyableInstoreAndOnline
    0.89
    quickShipAvailable
    0.87
    soft
    0.81
    pos
    0.78
    tesy
    0.77
    Nap
    0.77
    soType
    0.77
    Act Density 0.014%

    No Known Activations