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

    Neuronpedia

    INDEX
    Explanations

    words related to electronic security and technological aspects

    oai_token-act-pair · gpt-3.5-turbo

    the end of sections in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sth
    -0.75
    swer
    -0.65
     candle
    -0.65
     remembrance
    -0.64
    vironment
    -0.64
     belt
    -0.63
     Lyme
    -0.62
    cation
    -0.61
     household
    -0.61
     contender
    -0.61
    POSITIVE LOGITS
    ratch
    1.37
    ulpt
    1.34
    attered
    1.28
    oops
    1.26
    apers
    1.26
    reens
    1.25
    enario
    1.24
    outing
    1.20
    reenshots
    1.19
    ammers
    1.19
    Act Density 0.021%

    No Known Activations