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

    Neuronpedia

    INDEX
    Explanations

    informal contexts or settings

    oai_token-act-pair · gpt-3.5-turbo

    references to informal settings or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.73
    =-=-=-=-=-=-=-=-
    -0.70
    hma
    -0.69
    ebook
    -0.69
     Tycoon
    -0.68
     Glory
    -0.68
    ï¸
    -0.66
    metics
    -0.65
    RAM
    -0.65
    DVD
    -0.64
    POSITIVE LOGITS
     informal
    1.24
    yip
    0.78
    ensical
    0.78
     formal
    0.77
     gatherings
    0.73
     pneum
    0.70
    ormal
    0.69
     gathering
    0.68
    atural
    0.68
    odox
    0.68
    Act Density 0.004%

    No Known Activations