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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals have met someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "met."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     untreated
    -0.64
    leasing
    -0.60
     commentary
    -0.60
     citation
    -0.59
    otine
    -0.59
     membranes
    -0.59
    mort
    -0.59
     Parables
    -0.58
    vernment
    -0.57
     escaping
    -0.57
    POSITIVE LOGITS
    amorph
    1.29
    ropolis
    0.91
    ioned
    0.90
    agame
    0.85
    tle
    0.79
    ees
    0.78
     him
    0.77
    ered
    0.72
    atars
    0.70
    ups
    0.68
    Act Density 0.053%

    No Known Activations