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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to positive attributes or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    references to hidden or obscure items, often termed as "gems"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    aos
    -0.63
    onday
    -0.63
    abama
    -0.62
    avery
    -0.62
    ploy
    -0.61
     Capacity
    -0.61
     Wage
    -0.60
    acas
    -0.59
    POSITIVE LOGITS
     obscure
    1.28
     overlooked
    1.13
     surprises
    1.12
     favorites
    1.09
     irrelevant
    1.06
     downright
    1.05
     insignificant
    1.03
     lesser
    1.02
     unexpected
    1.02
     unrelated
    1.01
    Act Density 0.552%

    No Known Activations