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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to technology, specifically those related to digital files or software functions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "box" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDENT
    -0.78
    awar
    -0.75
    isance
    -0.72
    pling
    -0.68
    ittee
    -0.66
     pestic
    -0.64
     Lif
    -0.62
    orescence
    -0.62
     cort
    -0.61
    IELD
    -0.61
    POSITIVE LOGITS
    ansas
    0.95
    ed
    0.86
    360
    0.86
    xon
    0.85
    er
    0.85
    door
    0.84
    box
    0.84
    ertodd
    0.80
    erness
    0.80
    buster
    0.79
    Act Density 0.013%

    No Known Activations