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

    Neuronpedia

    INDEX
    Explanations

    sentences continuing a text with an introduction and clearly marked sections

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that suggest ongoing or repeated actions/events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compan
    -0.68
    mbuds
    -0.65
    romy
    -0.64
    boro
    -0.64
     undisclosed
    -0.62
     unsuspecting
    -0.61
    userc
    -0.61
     Barcl
    -0.61
    orkshire
    -0.61
     homebrew
    -0.60
    POSITIVE LOGITS
    VERTISEMENT
    0.83
    ccording
    0.77
    eria
    0.73
    Job
    0.70
     Marino
    0.69
    istration
    0.68
     ..........
    0.66
    =-=-=-=-
    0.65
    Gener
    0.64
    AIN
    0.62
    Act Density 0.033%

    No Known Activations