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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to unspecified or general concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOM
    -0.74
    sels
    -0.68
    oÄŁ
    -0.64
    DOS
    -0.64
    nor
    -0.63
     Ship
    -0.63
    ean
    -0.62
    inders
    -0.62
    mans
    -0.62
    mast
    -0.62
    POSITIVE LOGITS
    Else
    1.08
     else
    1.03
     intangible
    0.84
     akin
    0.79
     worthwhile
    0.75
    ĪĴ
    0.74
     disruptive
    0.74
     contagious
    0.73
     Else
    0.73
    ioned
    0.73
    Act Density 0.036%

    No Known Activations