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

    Neuronpedia

    INDEX
    Explanations

    page numbers

    oai_token-act-pair · gpt-3.5-turbo

    page references or numbers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.92
    ALLY
    -0.89
    eware
    -0.77
    dayName
    -0.73
    iques
    -0.73
    oise
    -0.73
    say
    -0.72
    Interstitial
    -0.71
    eatures
    -0.71
    creen
    -0.70
    POSITIVE LOGITS
    antry
    1.09
    Page
    0.81
     Page
    0.79
    views
    0.76
     McConnell
    0.69
     pancakes
    0.69
     Six
    0.67
    Rank
    0.66
    antom
    0.65
     subp
    0.64
    Act Density 0.016%

    No Known Activations