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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating superiority or addition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an ascending ranking or hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chie
    -0.69
    ELL
    -0.65
     Strait
    -0.62
    isher
    -0.62
     Breed
    -0.58
     Bye
    -0.57
    cci
    -0.57
     Guinness
    -0.57
    jab
    -0.57
    ITED
    -0.56
    POSITIVE LOGITS
    boards
    0.87
     thereof
    0.86
    oft
    0.86
     of
    0.83
    ography
    0.79
    most
    0.78
    mast
    0.77
    deck
    0.76
    retty
    0.75
    Of
    0.73
    Act Density 0.022%

    No Known Activations