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

    Neuronpedia

    INDEX
    Explanations

    mentions of technology components or specifications

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific symbol or character frequently found in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.76
    wagen
    -0.75
     Jeanne
    -0.71
     Marble
    -0.70
     Dupl
    -0.68
     Mirage
    -0.67
     mosqu
    -0.67
     Bris
    -0.67
     Sapphire
    -0.66
     grips
    -0.65
    POSITIVE LOGITS
    ¹
    1.00
    Ĵ
    0.96
    ij
    0.95
    ı
    0.94
    ł
    0.94
    ª
    0.94
    ¼
    0.88
    į
    0.88
    most
    0.88
    IJ
    0.86
    Act Density 0.119%

    No Known Activations