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

    Neuronpedia

    INDEX
    Explanations

    biographical information about individuals

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions indicating continuity or connection in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >[
    -0.79
    ptoms
    -0.69
    blance
    -0.69
    icators
    -0.67
    yip
    -0.66
    ãĤº
    -0.66
    icate
    -0.65
    awks
    -0.65
    ize
    -0.64
    abus
    -0.63
    POSITIVE LOGITS
     oversaw
    1.28
     participated
    1.28
     toured
    1.18
     worked
    1.17
     served
    1.15
     became
    1.14
     underwent
    1.12
     helped
    1.07
     undertook
    1.06
     owns
    1.04
    Act Density 0.183%

    No Known Activations