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

    Neuronpedia

    INDEX
    Explanations

    sentences with the word "two" or phrases indicating dual aspects/topics/parts

    oai_token-act-pair · gpt-3.5-turbo

    sentences that mention quantities or lists of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wonders
    -0.66
     billions
    -0.58
    enance
    -0.55
    oro
    -0.55
    rup
    -0.54
    letes
    -0.54
    earch
    -0.54
    unning
    -0.53
     millions
    -0.53
    uble
    -0.52
    POSITIVE LOGITS
     Firstly
    1.32
     Both
    1.25
     One
    1.19
    one
    1.19
    first
    1.09
    Firstly
    1.08
     one
    1.08
    Both
    1.07
    One
    1.01
     Neither
    1.00
    Act Density 0.285%

    No Known Activations