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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the act of purification or purging

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of purification or cleansing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    areth
    -0.71
     Standing
    -0.70
     Unch
    -0.70
    ONES
    -0.68
    lihood
    -0.68
     Stub
    -0.67
    olson
    -0.64
     Eisen
    -0.64
    ETF
    -0.64
    enegger
    -0.62
    POSITIVE LOGITS
    ple
    1.21
    vey
    1.15
    ples
    1.07
    ported
    1.07
    cell
    1.02
    pose
    1.01
    porting
    1.01
    fect
    1.01
    posed
    1.00
    pling
    0.99
    Act Density 0.022%

    No Known Activations